GlianaAI (1)

Download OpenAPI specification:

Gliana Labs: contact@glianalabs.com URL: https://ai.glianalabs.com

Pay-per-call AI inference across generative-media models. No signup or API key; each call is settled over MPP. Per-model prices: GET /v1/price?model=. Rate limit ~120 requests/min per IP — need more? contact@glianalabs.com.

GlianaAI

media

Generative media inference.

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

image-to-video

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate a video from a text prompt or an image.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/wan-2.7-i2v path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "wan-2.7-i2v",
"prompt": "a timelapse of clouds over mountains"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate a video with wan-2.7-i2v via x402.

$0.360000–$2.700000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call wan-2.7-i2v (image-to-video). Priced per second ($0.180000/sec) — final price = video length x rate (duration 2-15s).

Request Body schema: application/json
required

duration	integer [ 2 .. 15 ] Length of the output in seconds.
image required	string Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
negative_prompt	string What to avoid in the output.
prompt	string Text prompt describing what to generate.
resolution	string Enum: "720P" "1080P" Output resolution / quality tier.
seed	integer [ 0 .. 2147483647 ] Random seed for reproducible results — same seed + inputs gives the same output.
watermark	boolean Whether to add a watermark to the output.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image": "https://example.com/input.jpg"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with hh1-i2v via x402.

$1.218000–$6.090000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call hh1-i2v (image-to-video). Priced per second ($0.406000/sec) — final price = video length x rate (duration 3-15s).

Request Body schema: application/json
required

duration	integer [ 3 .. 15 ] Length of the output in seconds.
image required	string Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
negative_prompt	string What to avoid in the output.
prompt	string Text prompt describing what to generate.
resolution	string Enum: "720P" "1080P" Output resolution / quality tier.
seed	integer [ 0 .. 2147483647 ] Random seed for reproducible results — same seed + inputs gives the same output.
watermark	boolean Whether to add a watermark to the output.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image": "https://example.com/input.jpg"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with hh1.1-i2v via x402.

$0.783000–$3.915000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call hh1.1-i2v (image-to-video). Priced per second ($0.261000/sec) — final price = video length x rate (duration 3-15s).

Request Body schema: application/json
required

image required	string Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt	string Text prompt describing what to generate.
negative_prompt	string What to avoid in the output.
resolution	string Enum: "720P" "1080P" Output resolution / quality tier.
duration	integer [ 3 .. 15 ] Length of the output in seconds.
seed	integer [ 0 .. 2147483647 ] Random seed for reproducible results — same seed + inputs gives the same output.
watermark	boolean Whether to add a watermark to the output.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image": "https://example.com/input.jpg"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with hh1.1-r2v via x402.

$0.783000–$3.915000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call hh1.1-r2v (image-to-video). Priced per second ($0.261000/sec) — final price = video length x rate (duration 3-15s).

Request Body schema: application/json
required

prompt required	string Text prompt describing what to generate.
images required	Array of strings <uri> [ items <uri > ] Reference images to guide generation. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
resolution	string Enum: "720P" "1080P" Output resolution / quality tier.
ratio	string Enum: "16:9" "9:16" "3:4" "4:3" "1:1" "21:9" "9:21" "5:4" "4:5" Output aspect ratio.
duration	integer [ 3 .. 15 ] Length of the output in seconds.
seed	integer [ 0 .. 2147483647 ] Random seed for reproducible results — same seed + inputs gives the same output.
watermark	boolean Whether to add a watermark to the output.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table",
"images": ["https://example.com/input.jpg"
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with hailuo-2.3-fast via x402.

$0.079750–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call hailuo-2.3-fast (image-to-video). Priced per second ($0.079750/sec) — final price = video length x rate.

Request Body schema: application/json
required

duration	number Enum: 6 10 Length of the output in seconds.
fast_pretreatment	boolean Faster input pre-processing (may trade a little quality for speed).
first_frame_image required	string URL or base64 data URI of the first frame image Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt	string Text prompt describing what to generate.
prompt_optimizer	boolean Let the model automatically optimize your prompt.
resolution	string Enum: "768P" "1080P" Output resolution / quality tier.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"first_frame_image": "https://example.com/input.jpg"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

music

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate music from a text prompt with any model.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/music-2.6 path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "music-2.6",
"prompt": "a calm lo-fi beat"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate music with music-2.6 via x402.

$0.192000 per call. Flat price, charged only on success.

Pay-per-call music-2.6 (music).

Request Body schema: application/json
required

bitrate	number Enum: 32000 64000 128000 256000 Audio bitrate
format	string Enum: "mp3" "wav" Audio format
is_instrumental	boolean Generate instrumental music (no vocals)
lyrics	string Song lyrics, using \n to separate lines
lyrics_optimizer	boolean Automatically generate lyrics based on the prompt description
prompt required	string Description of the music style, mood, and scenario
sample_rate	number Enum: 16000 24000 32000 44100 Audio sample rate
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate music with music-v2 via x402.

$0.003000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call music-v2 (music). Priced per second ($0.003000/sec) — final price = video length x rate.

Request Body schema: application/json
required

prompt	string Text prompt describing what to generate.
composition_plan	object
music_length_ms	integer [ 3000 .. 600000 ]
output_format	string Enum: "auto" "mp3_48000_128" "mp3_48000_192" "mp3_48000_240" "mp3_48000_320" "mp3_22050_32" "mp3_24000_48" "mp3_44100_32" "mp3_44100_64" "mp3_44100_96" "mp3_44100_128" "mp3_44100_192" "opus_48000_32" "opus_48000_64" "opus_48000_96" "opus_48000_128" "opus_48000_192" File format of the output (e.g. png, jpeg, mp4).
seed	integer [ 0 .. 4294967295 ] Random seed for reproducible results — same seed + inputs gives the same output.
force_instrumental	boolean
store_for_inpainting	boolean
sign_with_c2pa	boolean
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

stt

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Transcribe audio to text with any STT model.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/grok-stt path also works. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-stt",
"audio_url": "https://example.com/input.mp3"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Transcribe audio with grok-stt via x402.

$0.009006 per call. Flat price, charged only on success.

Pay-per-call grok-stt (stt).

Request Body schema: application/json
required

audio_format	string Enum: "pcm" "mulaw" "alaw" Format hint for raw/headerless audio. Required for pcm, mulaw, alaw. Omit for container formats (mp3, wav, etc.) — xAI auto-detects them.
channels	integer [ 2 .. 8 ] Number of audio channels (2–8). Required only for multichannel raw audio; auto-detected for container formats.
diarize	boolean When true, enables speaker diarization. Each word in the response includes a `speaker` integer identifying the detected speaker.
file	string Audio file as a data URI (data:audio/...;base64,...) or an HTTPS URL the gateway fetches and uploads. Supported container formats: flac, mp3, mp4, m4a, mkv, ogg, opus, wav, aac. Raw formats (pcm, mulaw, alaw) also accepted — supply audio_format and sample_rate. Gateway-side size limit: 25 MB. Mutually exclusive with `url`. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
filler_words	boolean When true, filler words (uh, um, er) are included in the transcript. Defaults to false — filler words are removed.
format	boolean When true, enables Inverse Text Normalization — spoken numbers and currencies are converted to written form (e.g. "one hundred dollars" → "$100"). Requires language to be set.
keyterm	Array of arrays Key terms to bias transcription toward (e.g. product names, proper nouns). Each term up to 50 characters, max 100 terms. Sent as repeated form fields: keyterm=Term+One&keyterm=Term+Two.
language	string Language code (e.g. "en", "fr", "de"). Used with format=true to enable Inverse Text Normalization. xAI transcribes in any language regardless — supplying this enables number/currency formatting in the transcript.
multichannel	boolean When true, each audio channel is transcribed independently. Results are returned in the `channels` array. Requires channels ≥ 2.
sample_rate	integer Sample rate in Hz. Required when audio_format is set.
url	string HTTPS URL of an audio file for xAI to fetch server-side. Mutually exclusive with `file` and `websocket`. No gateway-side size limit applies. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{ }

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Transcribe audio with gpt-4o-transcribe via x402.

$0.032400 per call. Flat price, charged only on success.

Pay-per-call gpt-4o-transcribe (stt).

Request Body schema: application/json
required

file required	string The audio file as a data URI (data:audio/...;base64,...) or HTTPS URL. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
language	string The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
prompt	string An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
temperature	number [ 0 .. 1 ] The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Defaults to 0 if omitted.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"file": "https://example.com/input"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Transcribe audio with universal-3-pro via x402.

$0.018900 per call. Flat price, charged only on success.

Pay-per-call universal-3-pro (stt).

Request Body schema: application/json
required

audio_end_at	integer >= 0 Timestamp (in milliseconds) to end transcription at.
audio_start_from	integer >= 0 Timestamp (in milliseconds) to start transcription from.
audio_url required	string The URL of the audio file to transcribe. Can be a publicly accessible URL or a data URI (data:audio/...;base64,...). For data URIs, the audio will be uploaded to AssemblyAI automatically. Required for pre-recorded transcription (when stream is false or not set). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
auto_chapters	boolean Enable automatic chapter detection.
auto_highlights	boolean Enable automatic extraction of key phrases and highlights.
boost_param	string Enum: "low" "default" "high" How much to boost the words in word_boost.
content_safety	boolean Enable content safety detection for sensitive content.
custom_spelling	Array of arrays Custom spelling rules to replace specific words or phrases in the transcription output.
disfluencies	boolean Include filler words like "um", "uh", etc. in the transcript.
domain	string Value: "medical-v1" Domain-specific transcription mode. "medical-v1" enables medical terminology optimization.
dual_channel	boolean Process audio as dual-channel (stereo) for better accuracy.
entity_detection	boolean Enable detection of entities like names, organizations, and locations.
filter_profanity	boolean Filter profanity from the transcription.
iab_categories	boolean Enable IAB (Interactive Advertising Bureau) content taxonomy classification.
keyterms_prompt	Array of arrays An array of up to 1,000 words or phrases (max 6 words per phrase) to improve transcription accuracy. Cannot be used with the prompt parameter.
language_code	string The language code for the audio file (e.g., "en", "es", "fr"). Defaults to automatic language detection.
language_detection	boolean Enable automatic language detection. When enabled with speech_models, the system will automatically select the best model for the detected language.
multichannel	boolean Process each audio channel separately for multi-channel audio files.
prompt	string A custom prompt to guide transcription style, formatting, and output characteristics. Maximum 1,500 words.
redact_pii	boolean Redact personally identifiable information.
redact_pii_audio	boolean Generate a redacted audio file with PII removed.
redact_pii_policies	Array of arrays Specific PII policies to apply for redaction.
redact_pii_sub	string Enum: "entity_name" "hash" Strategy for substituting redacted PII.
sentiment_analysis	boolean Enable sentiment analysis for each sentence.
speaker_labels	boolean Enable speaker diarization to identify different speakers in the audio.
speakers_expected	integer >= 1 Expected number of speakers for speaker diarization.
speech_threshold	number [ 0 .. 1 ] Confidence threshold for speech detection.
temperature	number [ 0 .. 1 ] Controls randomness in model output (0.0-1.0). Lower values make output more deterministic. Default is 0.0.
webhook_url	string URL to receive webhook notifications when transcription is complete.
word_boost	Array of arrays Array of words to boost recognition accuracy (legacy - use keyterms_prompt instead).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"audio_url": "https://example.com/input.mp3"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

text-to-image

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate an image from a text prompt with any model.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/flux-2-pro-preview path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "flux-2-pro-preview",
"prompt": "a red apple on a wooden table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate an image with flux-2-pro-preview via x402.

$0.054000 per call. Flat price, charged only on success.

Pay-per-call flux-2-pro-preview (text-to-image).

Request Body schema: application/json
required

height	integer >= 64 Height of the generated image in pixels (minimum 64). Omit to let BFL pick.
input_images	Array of strings <uri> [ items <uri > ] Up to 8 reference images for editing or multi-image composition. Each entry is an HTTPS URL or a data:image/...;base64,... URI. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
output_format	string Enum: "jpeg" "png" "webp" Output image format. Defaults to jpeg.
prompt required	string Text prompt for image generation or editing.
safety_tolerance	integer [ 0 .. 5 ] Tolerance for input/output moderation. 0 is the strictest, 5 the most permissive. Defaults to 2.
seed	integer Optional seed for reproducible generation.
width	integer >= 64 Width of the generated image in pixels (minimum 64). Omit to let BFL pick.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with flux-2-max via x402.

$0.126000 per call. Flat price, charged only on success.

Pay-per-call flux-2-max (text-to-image).

Request Body schema: application/json
required

height	integer >= 64 Height of the generated image in pixels (minimum 64). Omit to let BFL pick.
input_images	Array of strings <uri> [ items <uri > ] Up to 8 reference images for editing or multi-image composition. Each entry is an HTTPS URL or a data:image/...;base64,... URI. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
output_format	string Enum: "jpeg" "png" "webp" Output image format. Defaults to jpeg.
prompt required	string Text prompt for image generation or editing.
safety_tolerance	integer [ 0 .. 5 ] Tolerance for input/output moderation. 0 is the strictest, 5 the most permissive. Defaults to 2.
seed	integer Optional seed for reproducible generation.
width	integer >= 64 Width of the generated image in pixels (minimum 64). Omit to let BFL pick.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with flux-2-flex via x402.

$0.090000 per call. Flat price, charged only on success.

Pay-per-call flux-2-flex (text-to-image).

Request Body schema: application/json
required

guidance	number [ 1.5 .. 10 ] Classifier-free guidance scale (1.5–10). Higher values follow the prompt more strictly at the cost of realism.
height	integer >= 64 Height of the generated image in pixels (minimum 64). Omit to let BFL pick.
input_images	Array of strings <uri> [ items <uri > ] Up to 8 reference images for editing or multi-image composition. Each entry is an HTTPS URL or a data:image/...;base64,... URI. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
output_format	string Enum: "jpeg" "png" "webp" Output image format. Defaults to jpeg.
prompt required	string Text prompt for image generation or editing.
prompt_upsampling	boolean Whether BFL should expand short prompts before generation. Defaults to true on flex.
safety_tolerance	integer [ 0 .. 5 ] Tolerance for input/output moderation. 0 is the strictest, 5 the most permissive. Defaults to 2.
seed	integer Optional seed for reproducible generation.
steps	integer [ 1 .. 50 ] Number of denoising steps (1–50). Higher steps yield more detail at the cost of latency.
width	integer >= 64 Width of the generated image in pixels (minimum 64). Omit to let BFL pick.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with grok-imagine-image-quality via x402.

$0.060000 per call. Flat price, charged only on success.

Pay-per-call grok-imagine-image-quality (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "3:4" "4:3" "9:16" "16:9" "2:3" "3:2" "9:19.5" "19.5:9" "9:20" "20:9" "1:2" "2:1" "auto" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
image	object Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
images	Array of strings <uri> [ items <uri > ] Reference images to guide generation. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
mask	object Mask image marking the region to edit (inpaint). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
n	integer [ 1 .. 10 ] How many outputs to generate.
prompt required	string Text prompt describing what to generate.
quality	string Enum: "low" "medium" "high" Output quality level.
resolution	string Enum: "1k" "2k" Output resolution / quality tier.
response_format	string Enum: "url" "b64_json" How the result is returned (e.g. a URL or base64 data).
user	string Optional end-user identifier for abuse monitoring; not required.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with grok-imagine-image via x402.

$0.024000 per call. Flat price, charged only on success.

Pay-per-call grok-imagine-image (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "3:4" "4:3" "9:16" "16:9" "2:3" "3:2" "9:19.5" "19.5:9" "9:20" "20:9" "1:2" "2:1" "auto" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
image	object Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
images	Array of strings <uri> [ items <uri > ] Reference images to guide generation. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
mask	object Mask image marking the region to edit (inpaint). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
n	integer [ 1 .. 10 ] How many outputs to generate.
prompt required	string Text prompt describing what to generate.
quality	string Enum: "low" "medium" "high" Output quality level.
resolution	string Enum: "1k" "2k" Output resolution / quality tier.
response_format	string Enum: "url" "b64_json" How the result is returned (e.g. a URL or base64 data).
user	string Optional end-user identifier for abuse monitoring; not required.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-pro via x402.

$0.450000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-pro (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-vector via x402.

$0.144000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-vector (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-pro-vector via x402.

$0.540000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-pro-vector (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1-vector via x402.

$0.144000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1-vector (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1-utility-vector via x402.

$0.144000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1-utility-vector (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1-utility-pro via x402.

$0.450000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1-utility-pro (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1-utility-pro-vector via x402.

$0.540000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1-utility-pro-vector (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1-pro-vector via x402.

$0.540000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1-pro-vector (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1-utility via x402.

$0.072000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1-utility (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1 via x402.

$0.072000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1 (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4-1-pro via x402.

$0.450000 per call. Flat price, charged only on success.

Pay-per-call recraftv4-1-pro (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv4 via x402.

$0.072000 per call. Flat price, charged only on success.

Pay-per-call recraftv4 (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with recraftv3 via x402.

$0.072000 per call. Flat price, charged only on success.

Pay-per-call recraftv3 (text-to-image).

Request Body schema: application/json
required

controls	object Advanced generation controls (style, color, and artistic settings).
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
style	string Visual style preset to apply.
substyle	string A finer style variant within the chosen style.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with gpt-image-2 via x402.

$0.048000 per call. Flat price, charged only on success.

Pay-per-call gpt-image-2 (text-to-image).

Request Body schema: application/json
required

background	string Enum: "opaque" "auto" Background transparency setting. Use transparent for images with no background, opaque for a solid background, or auto to let the model decide.
images	Array of strings <uri> [ items <uri > ] Input images for image editing, 1-16 entries. Each entry is base64-encoded (raw string or data:image/{png\|jpeg\|webp};base64,... URI). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
output_format	string Enum: "png" "webp" "jpeg" Output format for the generated image
prompt required	string Text prompt describing the image to generate or edit
quality	string Enum: "low" "medium" "high" "auto" Quality of the generated image
size	string Enum: "1024x1024" "1024x1536" "1536x1024" "auto" Size of the generated image
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with gpt-image-1.5 via x402.

$0.048000 per call. Flat price, charged only on success.

Pay-per-call gpt-image-1.5 (text-to-image).

Request Body schema: application/json
required

images	Array of strings <uri> [ items <uri > ] Input images for image editing, 1-16 entries. Each entry is base64-encoded (raw string or data:image/{png\|jpeg\|webp};base64,... URI). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt required	string Text prompt describing the image to generate or edit
quality	string Enum: "low" "medium" "high" "auto" Quality of the generated image
size	string Enum: "256x256" "512x512" "1024x1024" "1792x1024" "1024x1792" Size of the generated image
style	string Enum: "vivid" "natural" Style of the generated image
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with nano-banana-pro via x402.

$0.186000 per call. Flat price, charged only on success.

Pay-per-call nano-banana-pro (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "3:2" "2:3" "3:4" "4:3" "4:5" "5:4" "9:16" "16:9" "21:9" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
image_input	Array of strings <uri> [ items <uri > ] Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
image_size	string Enum: "1K" "2K" "4K" Output image dimensions.
output_format	string Enum: "jpg" "png" "webp" File format of the output (e.g. png, jpeg, mp4).
prompt required	string Text prompt describing what to generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with nano-banana via x402.

$0.046800 per call. Flat price, charged only on success.

Pay-per-call nano-banana (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "3:2" "2:3" "3:4" "4:3" "4:5" "5:4" "9:16" "16:9" "21:9" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
image_input	Array of strings <uri> [ items <uri > ] Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
image_size	string Enum: "1K" "2K" "4K" Output image dimensions.
output_format	string Enum: "jpg" "png" "webp" File format of the output (e.g. png, jpeg, mp4).
prompt required	string Text prompt describing what to generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with brainrot-character via x402.

$0.200000 per call. Flat price, charged only on success.

Pay-per-call brainrot-character (text-to-image).

Request Body schema: application/json
required

reference_image	string Optional reference image — the character is built FROM it (brainrot-ified). Pass a public URL, or upload a local file (free) via POST /v1/media (≤40MB) and pass the returned url. Omit for a hyper-random ORIGINAL character.
seed	integer Optional seed to reproduce the same random original; omit for a new one each call.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{ }

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with nano-banana-2 via x402.

$0.114000 per call. Flat price, charged only on success.

Pay-per-call nano-banana-2 (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "match_input_image" "1:1" "2:3" "3:2" "3:4" "4:3" "4:5" "5:4" "9:16" "16:9" "21:9" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
google_search	boolean Allow the model to use Google Search for grounding.
image_input	Array of strings <uri> [ items <uri > ] Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
image_search	boolean Allow the model to search for reference images.
output_format	string Enum: "jpg" "png" File format of the output (e.g. png, jpeg, mp4).
prompt required	string Text prompt describing what to generate.
resolution	string Enum: "1K" "2K" "4K" Output resolution / quality tier.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with imagen-4 via x402.

$0.072000 per call. Flat price, charged only on success.

Pay-per-call imagen-4 (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "3:4" "4:3" "9:16" "16:9" Aspect ratio of the generated image
person_generation	string Enum: "dont_allow" "allow_adult" "allow_all" Allow the model to generate images of people. dont_allow: block people, allow_adult: adults only, allow_all: adults and children
prompt required	string Text prompt describing the image to generate
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with seedream-4.5 via x402.

$0.072000 per call. Flat price, charged only on success.

Pay-per-call seedream-4.5 (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "match_input_image" "1:1" "4:3" "3:4" "16:9" "9:16" "3:2" "2:3" "21:9" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
disable_safety_checker	boolean Turn off the safety filter on outputs.
image_input	Array of strings <uri> [ items <uri > ] Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
max_images	integer [ 1 .. 15 ] Maximum number of images to return.
prompt required	string Text prompt describing what to generate.
sequential_image_generation	string Enum: "disabled" "auto" Generate a sequence of related images.
size	string Enum: "2K" "4K" Output dimensions (width × height).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with seedream-5-lite via x402.

$0.063000 per call. Flat price, charged only on success.

Pay-per-call seedream-5-lite (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "match_input_image" "1:1" "4:3" "3:4" "16:9" "9:16" "3:2" "2:3" "21:9" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
image_input	Array of strings <uri> [ items <uri > ] Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
max_images	integer [ 1 .. 15 ] Maximum number of images to return.
output_format	string Enum: "png" "jpeg" File format of the output (e.g. png, jpeg, mp4).
prompt required	string Text prompt describing what to generate.
sequential_image_generation	string Enum: "disabled" "auto" Generate a sequence of related images.
size	string Enum: "2K" "3K" Output dimensions (width × height).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with seedream-4.0 via x402.

$0.054000 per call. Flat price, charged only on success.

Pay-per-call seedream-4.0 (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "match_input_image" "1:1" "4:3" "3:4" "16:9" "9:16" "3:2" "2:3" "21:9" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enhance_prompt	boolean Let the model automatically expand/improve your prompt.
height	integer [ 1024 .. 4096 ] Output height in pixels.
prompt required	string Text prompt describing what to generate.
size	string Enum: "1K" "2K" "4K" "custom" Output dimensions (width × height).
width	integer [ 1024 .. 4096 ] Output width in pixels.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with wan-2.6-image via x402.

$0.054000 per call. Flat price, charged only on success.

Pay-per-call wan-2.6-image (text-to-image).

Request Body schema: application/json
required

negative_prompt	string What to avoid in the output.
prompt required	string Text prompt describing what to generate.
size	string Output dimensions (width × height).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with krea-2-medium-turbo via x402.

$0.018000 per call. Flat price, charged only on success.

Pay-per-call krea-2-medium-turbo (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "4:3" "3:2" "16:9" "2.35:1" "4:5" "2:3" "9:16" Aspect ratio of the generated image.
complexity	integer [ -100 .. 100 ] K2 Complexity slider (-100 to 100). 0 disables the slider LoRA.
creativity	string Enum: "raw" "low" "medium" "high" Prompt expansion mode. `raw` disables expansion; `low`, `medium`, `high` control strength. Does not affect the K2 Intensity, Complexity, or Movement slider LoRAs.
image_style_references	Array of strings <uri> [ items <uri > ] Reference images to drive the visual style (up to 10). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
intensity	integer [ -100 .. 100 ] K2 Intensity slider (-100 to 100). 0 disables the slider LoRA.
moodboards	Array of arrays Moodboard references (currently limited to one).
movement	integer [ -100 .. 100 ] K2 Movement slider (-100 to 100). 0 disables the slider LoRA.
prompt required	string Text prompt describing the image to generate.
resolution	string Value: "1K" Resolution scale.
seed	any Random seed for reproducible generations. Pass null or omit for a random seed.
styles	Array of arrays Styles (typically LoRAs) to apply to the generation.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with krea-2-medium via x402.

$0.036000 per call. Flat price, charged only on success.

Pay-per-call krea-2-medium (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "4:3" "3:2" "16:9" "2.35:1" "4:5" "2:3" "9:16" Aspect ratio of the generated image.
complexity	integer [ -100 .. 100 ] K2 Complexity slider (-100 to 100). 0 disables the slider LoRA.
creativity	string Enum: "raw" "low" "medium" "high" Prompt expansion mode. `raw` disables expansion; `low`, `medium`, `high` control strength. Does not affect the K2 Intensity, Complexity, or Movement slider LoRAs.
image_style_references	Array of strings <uri> [ items <uri > ] Reference images to drive the visual style (up to 10). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
intensity	integer [ -100 .. 100 ] K2 Intensity slider (-100 to 100). 0 disables the slider LoRA.
moodboards	Array of arrays Moodboard references (currently limited to one).
movement	integer [ -100 .. 100 ] K2 Movement slider (-100 to 100). 0 disables the slider LoRA.
prompt required	string Text prompt describing the image to generate.
resolution	string Value: "1K" Resolution scale.
seed	any Random seed for reproducible generations. Pass null or omit for a random seed.
styles	Array of arrays Styles (typically LoRAs) to apply to the generation.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with krea-2-large via x402.

$0.072000 per call. Flat price, charged only on success.

Pay-per-call krea-2-large (text-to-image).

Request Body schema: application/json
required

aspect_ratio	string Enum: "1:1" "4:3" "3:2" "16:9" "2.35:1" "4:5" "2:3" "9:16" Aspect ratio of the generated image.
complexity	integer [ -100 .. 100 ] K2 Complexity slider (-100 to 100). 0 disables the slider LoRA.
creativity	string Enum: "raw" "low" "medium" "high" Prompt expansion mode. `raw` disables expansion; `low`, `medium`, `high` control strength. Does not affect the K2 Intensity, Complexity, or Movement slider LoRAs.
image_style_references	Array of strings <uri> [ items <uri > ] Reference images to drive the visual style (up to 10). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
intensity	integer [ -100 .. 100 ] K2 Intensity slider (-100 to 100). 0 disables the slider LoRA.
moodboards	Array of arrays Moodboard references (currently limited to one).
movement	integer [ -100 .. 100 ] K2 Movement slider (-100 to 100). 0 disables the slider LoRA.
prompt required	string Text prompt describing the image to generate.
resolution	string Value: "1K" Resolution scale.
seed	any Random seed for reproducible generations. Pass null or omit for a random seed.
styles	Array of arrays Styles (typically LoRAs) to apply to the generation.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with seedream-5-pro via x402.

$0.054000 per call. Flat price, charged only on success.

Pay-per-call seedream-5-pro (text-to-image).

Request Body schema: application/json
required

prompt required	string Text prompt describing what to generate.
image	any Input image (HTTPS URL or upload) to guide or edit from.
size	string Output dimensions (width × height).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate an image with nano-banana-2-lite via x402.

$0.046440 per call. Flat price, charged only on success.

Pay-per-call nano-banana-2-lite (text-to-image).

Request Body schema: application/json
required

prompt required	string Text prompt describing what to generate.
image_input	Array of strings <uri> [ items <uri > ] Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
aspect_ratio	string Enum: "match_input_image" "1:1" "2:3" "3:2" "3:4" "4:3" "4:5" "5:4" "9:16" "16:9" "21:9" Output aspect ratio (e.g. 16:9, 1:1, 9:16).
output_format	string Enum: "jpg" "png" File format of the output (e.g. png, jpeg, mp4).
resolution	string Enum: "1K" "2K" "4K" Output resolution / quality tier.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

text-to-video

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate a video from a text prompt or an image.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/wan-2.7-i2v path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "wan-2.7-i2v",
"prompt": "a timelapse of clouds over mountains"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate a video with brainrot-video via x402.

$1.050000 per call. Flat price, charged only on success.

Pay-per-call brainrot-video (text-to-video).

Request Body schema: application/json
required

reference_image	string Optional reference image — the character is built FROM it (brainrot-ified), then animated. Pass a public URL, or upload a local file (free) via POST /v1/media (≤40MB). Omit for a hyper-random ORIGINAL character.
motionPrompt	string Optional description of how the character should move (default: chaotic dancing meme energy).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{ }

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with q3-pro via x402.

$0.217500–$3.480000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call q3-pro (text-to-video). Priced per second ($0.217500/sec) — final price = video length x rate (duration 1-16s).

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "9:16" "3:4" "4:3" "1:1" Video aspect ratio (text-to-video only). Default: 16:9
audio	boolean Enable audio-video synchronization. Default: true for Q3 models. When false, outputs silent video
duration	integer [ 1 .. 16 ] Video duration in seconds (1-16)
end_image	string End image for start/end-to-video generation. Must be used together with start_image. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt	string Text prompt describing what should appear in the video
resolution	string Enum: "540p" "720p" "1080p" Video resolution
start_image	string Start image for video generation. Use alone for image-to-video, or with end_image for start/end-to-video. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with q3-turbo via x402.

$0.101500–$1.624000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call q3-turbo (text-to-video). Priced per second ($0.101500/sec) — final price = video length x rate (duration 1-16s).

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "9:16" "3:4" "4:3" "1:1" Video aspect ratio (text-to-video only). Default: 16:9
audio	boolean Enable audio-video synchronization. Default: true for Q3 models. When false, outputs silent video
duration	integer [ 1 .. 16 ] Video duration in seconds (1-16)
end_image	string End image for start/end-to-video generation. Must be used together with start_image. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt	string Text prompt describing what should appear in the video
resolution	string Enum: "540p" "720p" "1080p" Video resolution
start_image	string Start image for video generation. Use alone for image-to-video, or with end_image for start/end-to-video. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with gen-4.5 via x402.

$0.522000–$2.610000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call gen-4.5 (text-to-video). Priced per second ($0.261000/sec) — final price = video length x rate (duration 2-10s).

Request Body schema: application/json
required

content_moderation	object Content moderation settings
duration	integer [ 2 .. 10 ] Video duration in seconds
image_input	string HTTPS URL, Runway URI, or data URI containing an image for image-to-video Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt required	string Text prompt describing what should appear in the video
ratio	string Enum: "1280:720" "720:1280" "1104:832" "960:960" "832:1104" "1584:672" Resolution/aspect ratio of the output video
seed	integer [ 0 .. 4294967295 ] Random seed for reproducible results
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with v6 via x402.

$0.166750–$2.501250 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call v6 (text-to-video). Priced per second ($0.166750/sec) — final price = video length x rate (duration 1-15s).

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "4:3" "1:1" "3:4" "9:16" "2:3" "3:2" "21:9" Video aspect ratio
duration	integer [ 1 .. 15 ] Video duration in seconds (1 to 15)
generate_audio	boolean Whether to generate audio with the video
image_input	string Base64-encoded reference image for image-to-video generation (data:image/...;base64,...). The image will be uploaded to Pixverse automatically. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
negative_prompt	string Negative text prompt
prompt required	string Text prompt describing the video to generate
quality	string Enum: "360p" "540p" "720p" "1080p" Video quality
seed	integer [ 0 .. 2147483647 ] Random seed for reproducibility
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with v5.6 via x402.

$0.217500–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call v5.6 (text-to-video). Priced per second ($0.217500/sec) — final price = video length x rate.

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "4:3" "1:1" "3:4" "9:16" "2:3" "3:2" "21:9" Video aspect ratio
duration	number Enum: 5 8 10 Video duration in seconds
generate_audio	boolean Whether to generate audio with the video
image_input	string Base64-encoded reference image for image-to-video generation (data:image/...;base64,...). The image will be uploaded to Pixverse automatically. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
motion_mode	string Enum: "normal" "fast" Motion mode (fast only available when duration=5; 1080p does not support fast)
negative_prompt	string Negative text prompt
prompt required	string Text prompt describing the video to generate
quality	string Enum: "360p" "540p" "720p" "1080p" Video quality
seed	integer [ 0 .. 2147483647 ] Random seed for reproducibility
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with hailuo-2.3 via x402.

$0.118418–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call hailuo-2.3 (text-to-video). Priced per second ($0.118418/sec) — final price = video length x rate.

Request Body schema: application/json
required

duration	number Enum: 6 10 Length of the output in seconds.
fast_pretreatment	boolean Faster input pre-processing (may trade a little quality for speed).
first_frame_image	string Image to use as the first frame of the video.
prompt	string Text prompt describing what to generate.
prompt_optimizer	boolean Let the model automatically optimize your prompt.
resolution	string Enum: "768P" "1080P" Output resolution / quality tier.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with veo-3.1-fast via x402.

$0.435000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call veo-3.1-fast (text-to-video). Priced per second ($0.435000/sec) — final price = video length x rate.

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "9:16" "1:1" Video aspect ratio
duration	string Enum: "4s" "6s" "8s" Video duration
generate_audio	boolean Whether to generate audio with the video
image_input	string Base64-encoded reference image for i2v Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt required	string Text prompt describing the video to generate
resolution	string Enum: "720p" "1080p" Video resolution
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with veo-3.1 via x402.

$0.870000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call veo-3.1 (text-to-video). Priced per second ($0.870000/sec) — final price = video length x rate.

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "9:16" "1:1" Video aspect ratio
duration	string Enum: "4s" "6s" "8s" Video duration
generate_audio	boolean Whether to generate audio with the video
image_input	string Base64-encoded reference image for i2v Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt required	string Text prompt describing the video to generate
resolution	string Enum: "720p" "1080p" Video resolution
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with seedance-2.0-fast via x402.

$0.986000–$2.958000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call seedance-2.0-fast (text-to-video). Priced per second ($0.246500/sec) — final price = video length x rate (duration 4-12s).

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "4:3" "1:1" "3:4" "9:16" "21:9" "9:21" Video aspect ratio. Ignored if an image is used.
camera_fixed	boolean Whether to fix camera position
duration	integer [ 4 .. 12 ] Video duration in seconds
fps	number Frame rate (frames per second)
generate_audio	boolean Whether to generate audio with the video
image	string Reference image (HTTP(S) URL or base64 data URI) for image-to-video Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
last_frame_image	string Reference image (HTTP(S) URL or base64 data URI) for last-frame guidance. Only works if an image start frame is also given. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt required	string Text prompt describing the video to generate
reference_images	Array of strings <uri> [ items <uri > ] Reference images (1-4, HTTP(S) URLs or base64 data URIs) to guide video generation for characters, avatars, clothing, or environments. Cannot be used with 1080p resolution or first/last frame images. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
reference_video	string Reference video (HTTP(S) URL or base64 data URI) for style/motion guidance Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
resolution	string Enum: "480p" "720p" Video resolution
seed	integer Random seed for reproducible generation
watermark	boolean Whether to add a watermark to the output video
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with seedance-2.0-mini via x402.

$0.638000–$1.914000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call seedance-2.0-mini (text-to-video). Priced per second ($0.159500/sec) — final price = video length x rate (duration 4-12s).

Request Body schema: application/json
required

prompt required	string Text prompt describing the video to generate
image	string Reference image (HTTP(S) URL or base64 data URI) for image-to-video Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
reference_video	string Reference video (HTTP(S) URL or base64 data URI) for style/motion guidance Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
last_frame_image	string Reference image (HTTP(S) URL or base64 data URI) for last-frame guidance. Only works if an image start frame is also given. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
reference_images	Array of strings <uri> [ items <uri > ] Reference images (1-4, HTTP(S) URLs or base64 data URIs) to guide video generation for characters, avatars, clothing, or environments. Cannot be used with 1080p resolution or first/last frame images. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
duration	integer [ 4 .. 12 ] Video duration in seconds
resolution	string Enum: "480p" "720p" Video resolution
aspect_ratio	string Enum: "16:9" "4:3" "1:1" "3:4" "9:16" "21:9" "9:21" Video aspect ratio. Ignored if an image is used.
fps	number Frame rate (frames per second)
camera_fixed	boolean Whether to fix camera position
generate_audio	boolean Whether to generate audio with the video
watermark	boolean Whether to add a watermark to the output video
seed	integer Random seed for reproducible generation
reference_audio	string Reference audio (HTTP(S) URL or base64 data:audio/... URI) to use as background music. Must be accompanied by a reference image or video. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with seedance-2.0 via x402.

$3.190000–$9.570000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call seedance-2.0 (text-to-video). Priced per second ($0.797500/sec) — final price = video length x rate (duration 4-12s).

Request Body schema: application/json
required

aspect_ratio	string Enum: "16:9" "4:3" "1:1" "3:4" "9:16" "21:9" "9:21" Video aspect ratio. Ignored if an image is used.
camera_fixed	boolean Whether to fix camera position
duration	integer [ 4 .. 12 ] Video duration in seconds
fps	number Frame rate (frames per second)
generate_audio	boolean Whether to generate audio with the video
image	string Reference image (HTTP(S) URL or base64 data URI) for image-to-video Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
last_frame_image	string Reference image (HTTP(S) URL or base64 data URI) for last-frame guidance. Only works if an image start frame is also given. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt required	string Text prompt describing the video to generate
reference_images	Array of strings <uri> [ items <uri > ] Reference images (1-4, HTTP(S) URLs or base64 data URIs) to guide video generation for characters, avatars, clothing, or environments. Cannot be used with 1080p resolution or first/last frame images. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
reference_video	string Reference video (HTTP(S) URL or base64 data URI) for style/motion guidance Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
resolution	string Enum: "480p" "720p" "1080p" Video resolution
seed	integer Random seed for reproducible generation
watermark	boolean Whether to add a watermark to the output video
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with hh1-t2v via x402.

$1.218000–$6.090000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call hh1-t2v (text-to-video). Priced per second ($0.406000/sec) — final price = video length x rate (duration 3-15s).

Request Body schema: application/json
required

duration	integer [ 3 .. 15 ] Length of the output in seconds.
prompt required	string Text prompt describing what to generate.
ratio	string Enum: "16:9" "9:16" "1:1" "4:3" "3:4" Output aspect ratio.
resolution	string Enum: "720P" "1080P" Output resolution / quality tier.
seed	integer [ 0 .. 2147483647 ] Random seed for reproducible results — same seed + inputs gives the same output.
watermark	boolean Whether to add a watermark to the output.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate a video with hh1.1-t2v via x402.

$0.783000–$3.915000 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call hh1.1-t2v (text-to-video). Priced per second ($0.261000/sec) — final price = video length x rate (duration 3-15s).

Request Body schema: application/json
required

prompt required	string Text prompt describing what to generate.
resolution	string Enum: "720P" "1080P" Output resolution / quality tier.
ratio	string Enum: "16:9" "9:16" "1:1" "4:3" "3:4" Output aspect ratio.
duration	integer [ 3 .. 15 ] Length of the output in seconds.
seed	integer [ 0 .. 2147483647 ] Random seed for reproducible results — same seed + inputs gives the same output.
watermark	boolean Whether to add a watermark to the output.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

tts

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Convert text to speech with any TTS model.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/grok-tts path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-tts",
"input": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Convert text to speech with grok-tts via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call grok-tts (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

language	string BCP-47 language code (e.g. "en", "zh", "pt-BR") or "auto" for automatic language detection. Required for both REST and WebSocket modes. Supported codes: auto, en, ar-EG, ar-SA, ar-AE, bn, zh, fr, de, hi, id, it, ja, ko, pt-BR, pt-PT, ru, es-MX, es-ES, tr, vi.
optimize_streaming_latency	number Enum: 0 1 Latency optimization for streaming synthesis. 0 (default): no optimization, best audio quality. 1: reduced first-chunk size for lower time-to-first-audio with minor quality tradeoff.
output_format	object Output audio format. Defaults to MP3 at 24 kHz / 128 kbps when omitted.
speed	number [ 0.7 .. 1.5 ] Speech speed multiplier. 1.0 is normal speed. Range: 0.7 to 1.5. Defaults to 1.0. Only used in WebSocket mode.
text required	string Text to convert to speech. Maximum 15,000 characters. Supports inline speech tags: [pause], [laugh], …, etc. Required for REST mode, mutually exclusive with websocket.
text_normalization	boolean When true, normalizes written-form text into spoken-form before synthesis (e.g. "Dr." → "Doctor", "100" → "one hundred"). Defaults to false.
voice_id	string Voice for synthesis. Defaults to "eve". Built-in voices: eve (energetic), ara (warm), rex (confident), sal (balanced), leo (authoritative). Custom voice IDs from /v1/tts/voices are also accepted. Case-insensitive — "Eve", "EVE", and "eve" are equivalent.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with tts-1-hd via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call tts-1-hd (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

response_format	string Enum: "mp3" "opus" "wav" "aac" "flac" The output format for the audio. Supported formats are mp3, opus, wav, aac and flac.
speed	number [ 0.25 .. 4 ] The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.
text required	string The text to generate audio for. Maximum length is 4096 characters.
voice	string Enum: "alloy" "echo" "fable" "onyx" "nova" "shimmer" The voice to use when generating the audio. Defaults to alloy.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with tts-1 via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call tts-1 (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

response_format	string Enum: "mp3" "opus" "wav" "aac" "flac" The output format for the audio. Supported formats are mp3, opus, wav, aac and flac.
speed	number [ 0.25 .. 4 ] The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.
text required	string The text to generate audio for. Maximum length is 4096 characters.
voice	string Enum: "alloy" "echo" "fable" "onyx" "nova" "shimmer" The voice to use when generating the audio. Defaults to alloy.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with speech-2.8-turbo via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call speech-2.8-turbo (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

emotion	string Enum: "happy" "sad" "angry" "fearful" "disgusted" "surprised" "calm" "fluent" Emotion control for synthesized speech
format	string Enum: "mp3" "flac" "wav" Output audio format
pitch	integer [ -12 .. 12 ] Pitch adjustment (-12 to 12)
sample_rate	number Enum: 8000 16000 22050 24000 32000 44100 Audio sample rate
speed	number [ 0.5 .. 2 ] Speech speed (0.5 to 2)
text required	string The text to convert to speech. Maximum 10,000 characters.
voice_id	string The voice ID to use for synthesis
volume	number [ 0 .. 10 ] Speech volume (0 to 10)
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with speech-2.8-hd via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call speech-2.8-hd (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

emotion	string Enum: "happy" "sad" "angry" "fearful" "disgusted" "surprised" "calm" "fluent" Emotion control for synthesized speech
format	string Enum: "mp3" "flac" "wav" Output audio format
pitch	integer [ -12 .. 12 ] Pitch adjustment (-12 to 12)
sample_rate	number Enum: 8000 16000 22050 24000 32000 44100 Audio sample rate
speed	number [ 0.5 .. 2 ] Speech speed (0.5 to 2)
text required	string The text to convert to speech. Maximum 10,000 characters.
voice_id	string The voice ID to use for synthesis
volume	number [ 0 .. 10 ] Speech volume (0 to 10)
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with tts-2 via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call tts-2 (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

apply_text_normalization	boolean When enabled, text normalization expands numbers, dates, times, and abbreviations before converting to speech. Turning this off may reduce latency.
bit_rate	integer Bits per second of the audio. Only for compressed audio formats (mp3, opus). The default is 128,000.
output_format	string Enum: "mp3" "opus" "wav" "flac" The output format for the audio. Supported formats are mp3, opus, wav, and flac. Defaults to mp3.
sample_rate	integer The synthesis sample rate in hertz. Accepts: 8000, 16000, 22050, 24000, 32000, 44100, 48000. The default is 48,000.
speaking_rate	number [ 0.5 .. 1.5 ] Speaking rate/speed, in the range [0.5, 1.5]. The default is 1.0. We recommend using values above 0.8 to ensure high quality.
temperature	number [ 0.01 .. 2 ] Determines the degree of randomness when sampling audio tokens. Defaults to 1.0. Accepts values between 0 (exclusive) and 2 (inclusive). Higher values = more expressive, lower values = more deterministic.
text required	string The text to be synthesized into speech. Maximum input of 2,000 characters.
timestamp_type	string Enum: "none" "word" "character" Controls timestamp metadata returned with the audio. "word" returns word-level timing, "character" returns character-level timing. Note: adds latency. Defaults to none.
voice_id	string Enum: "Loretta" "Darlene" "Marlene" "Hank" "Evelyn" "Celeste" "Pippa" "Tessa" "Liam" "Callum" "Hamish" "Abby" "Graham" "Rupert" "Mortimer" "Snik" "Anjali" "Saanvi" "Arjun" "Claire" "Oliver" "Simon" "Elliot" "James" "Serena" "Gareth" "Vinny" "Lauren" "Jessica" "Ethan" "Tyler" "Jason" "Chloe" "Veronica" "Victoria" "Miranda" "Sebastian" "Victor" "Malcolm" "Nate" "Brian" "Amina" "Kelsey" "Derek" "Evan" "Kayla" "Jake" "Grant" "Tristan" "Nadia" "Selene" "Marcus" "Riley" "Damon" "Cedric" "Mia" "Naomi" "Jonah" "Levi" "Avery" "Brandon" "Conrad" "Bianca" "Lucian" "Trevor" "Alex" "Ashley" "Craig" "Deborah" "Dennis" "Edward" "Elizabeth" "Hades" "Julia" "Pixie" "Mark" "Olivia" "Priya" "Ronald" "Sarah" "Shaun" "Theodore" "Timothy" "Wendy" "Dominus" "Hana" "Clive" "Carter" "Blake" "Luna" "Reed" "Duncan" "Felix" "Eleanor" "Sophie" The ID of the voice to use for synthesizing speech. Defaults to Dennis.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with tts-1.5-max via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call tts-1.5-max (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

apply_text_normalization	boolean When enabled, text normalization expands numbers, dates, times, and abbreviations before converting to speech. Turning this off may reduce latency.
bit_rate	integer Bits per second of the audio. Only for compressed audio formats (mp3, opus). The default is 128,000.
output_format	string Enum: "mp3" "opus" "wav" "flac" The output format for the audio. Supported formats are mp3, opus, wav, and flac. Defaults to mp3.
sample_rate	integer The synthesis sample rate in hertz. Accepts: 8000, 16000, 22050, 24000, 32000, 44100, 48000. The default is 48,000.
speaking_rate	number [ 0.5 .. 1.5 ] Speaking rate/speed, in the range [0.5, 1.5]. The default is 1.0. We recommend using values above 0.8 to ensure high quality.
temperature	number [ 0.01 .. 2 ] Determines the degree of randomness when sampling audio tokens. Defaults to 1.0. Accepts values between 0 (exclusive) and 2 (inclusive). Higher values = more expressive, lower values = more deterministic.
text required	string The text to be synthesized into speech. Maximum input of 2,000 characters.
timestamp_type	string Enum: "none" "word" "character" Controls timestamp metadata returned with the audio. "word" returns word-level timing, "character" returns character-level timing. Note: adds latency. Defaults to none.
voice_id	string Enum: "Loretta" "Darlene" "Marlene" "Hank" "Evelyn" "Celeste" "Pippa" "Tessa" "Liam" "Callum" "Hamish" "Abby" "Graham" "Rupert" "Mortimer" "Snik" "Anjali" "Saanvi" "Arjun" "Claire" "Oliver" "Simon" "Elliot" "James" "Serena" "Gareth" "Vinny" "Lauren" "Jessica" "Ethan" "Tyler" "Jason" "Chloe" "Veronica" "Victoria" "Miranda" "Sebastian" "Victor" "Malcolm" "Nate" "Brian" "Amina" "Kelsey" "Derek" "Evan" "Kayla" "Jake" "Grant" "Tristan" "Nadia" "Selene" "Marcus" "Riley" "Damon" "Cedric" "Mia" "Naomi" "Jonah" "Levi" "Avery" "Brandon" "Conrad" "Bianca" "Lucian" "Trevor" "Alex" "Ashley" "Craig" "Deborah" "Dennis" "Edward" "Elizabeth" "Hades" "Julia" "Pixie" "Mark" "Olivia" "Priya" "Ronald" "Sarah" "Shaun" "Theodore" "Timothy" "Wendy" "Dominus" "Hana" "Clive" "Carter" "Blake" "Luna" "Reed" "Duncan" "Felix" "Eleanor" "Sophie" The ID of the voice to use for synthesizing speech. Defaults to Dennis.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with tts-1.5-mini via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call tts-1.5-mini (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

apply_text_normalization	boolean When enabled, text normalization expands numbers, dates, times, and abbreviations before converting to speech. Turning this off may reduce latency.
bit_rate	integer Bits per second of the audio. Only for compressed audio formats (mp3, opus). The default is 128,000.
output_format	string Enum: "mp3" "opus" "wav" "flac" The output format for the audio. Supported formats are mp3, opus, wav, and flac. Defaults to mp3.
sample_rate	integer The synthesis sample rate in hertz. Accepts: 8000, 16000, 22050, 24000, 32000, 44100, 48000. The default is 48,000.
speaking_rate	number [ 0.5 .. 1.5 ] Speaking rate/speed, in the range [0.5, 1.5]. The default is 1.0. We recommend using values above 0.8 to ensure high quality.
temperature	number [ 0.01 .. 2 ] Determines the degree of randomness when sampling audio tokens. Defaults to 1.0. Accepts values between 0 (exclusive) and 2 (inclusive). Higher values = more expressive, lower values = more deterministic.
text required	string The text to be synthesized into speech. Maximum input of 2,000 characters.
timestamp_type	string Enum: "none" "word" "character" Controls timestamp metadata returned with the audio. "word" returns word-level timing, "character" returns character-level timing. Note: adds latency. Defaults to none.
voice_id	string Enum: "Loretta" "Darlene" "Marlene" "Hank" "Evelyn" "Celeste" "Pippa" "Tessa" "Liam" "Callum" "Hamish" "Abby" "Graham" "Rupert" "Mortimer" "Snik" "Anjali" "Saanvi" "Arjun" "Claire" "Oliver" "Simon" "Elliot" "James" "Serena" "Gareth" "Vinny" "Lauren" "Jessica" "Ethan" "Tyler" "Jason" "Chloe" "Veronica" "Victoria" "Miranda" "Sebastian" "Victor" "Malcolm" "Nate" "Brian" "Amina" "Kelsey" "Derek" "Evan" "Kayla" "Jake" "Grant" "Tristan" "Nadia" "Selene" "Marcus" "Riley" "Damon" "Cedric" "Mia" "Naomi" "Jonah" "Levi" "Avery" "Brandon" "Conrad" "Bianca" "Lucian" "Trevor" "Alex" "Ashley" "Craig" "Deborah" "Dennis" "Edward" "Elizabeth" "Hades" "Julia" "Pixie" "Mark" "Olivia" "Priya" "Ronald" "Sarah" "Shaun" "Theodore" "Timothy" "Wendy" "Dominus" "Hana" "Clive" "Carter" "Blake" "Luna" "Reed" "Duncan" "Felix" "Eleanor" "Sophie" The ID of the voice to use for synthesizing speech. Defaults to Dennis.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with gemini-3.1-flash-tts via x402.

$0.014400 per call. Flat price, charged only on success.

Pay-per-call gemini-3.1-flash-tts (tts).

Request Body schema: application/json
required

maxOutputTokens	integer >= 0 Maximum number of tokens to generate
stopSequences	Array of arrays Sequences where the model will stop generating further tokens
temperature	number [ 0 .. 2 ] Controls randomness in generation (0-2)
text required	string The text to convert to speech. Maximum 10,000 characters.
topK	integer >= 0 Only sample from the top K tokens. Smaller K = more focused, larger K = more diverse
topP	number [ 0 .. 1 ] Nucleus sampling threshold (0-1). Tokens with cumulative probability up to topP are considered
voice	string Enum: "Zephyr" "Puck" "Charon" "Kore" "Fenrir" "Leda" "Orus" "Aoede" "Callirrhoe" "Autonoe" "Enceladus" "Iapetus" "Umbriel" "Algieba" "Despina" "Erinome" "Algenib" "Rasalgethi" "Laomedeia" "Achernar" "Alnilam" "Schedar" "Gacrux" "Pulcherrima" "Achird" "Zubenelgenubi" "Vindemiatrix" "Sadachbia" "Sadaltager" "Sulafat" The voice to use for speech synthesis
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with eleven-v3 via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call eleven-v3 (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

text required	string The text to convert into speech.
voice_id	string The ElevenLabs voice ID to use for generation.
output_format	string Enum: "mp3_22050_32" "mp3_24000_48" "mp3_44100_128" "mp3_44100_192" "mp3_44100_32" "mp3_44100_64" "mp3_44100_96" "opus_48000_128" "opus_48000_192" "opus_48000_32" "opus_48000_64" "opus_48000_96" File format of the output (e.g. png, jpeg, mp4).
language_code	string ISO 639-1 language code to enforce.
voice_settings	object
seed	integer [ 0 .. 4294967295 ] Random seed for reproducible results — same seed + inputs gives the same output.
previous_text	string
next_text	string
apply_text_normalization	string Enum: "auto" "on" "off"
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with eleven-multilingual-v2 via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call eleven-multilingual-v2 (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

text required	string The text to convert into speech.
voice_id	string The ElevenLabs voice ID to use for generation.
output_format	string Enum: "mp3_22050_32" "mp3_24000_48" "mp3_44100_128" "mp3_44100_192" "mp3_44100_32" "mp3_44100_64" "mp3_44100_96" "opus_48000_128" "opus_48000_192" "opus_48000_32" "opus_48000_64" "opus_48000_96" File format of the output (e.g. png, jpeg, mp4).
language_code	string ISO 639-1 language code to enforce.
voice_settings	object
seed	integer [ 0 .. 4294967295 ] Random seed for reproducible results — same seed + inputs gives the same output.
previous_text	string
next_text	string
apply_text_normalization	string Enum: "auto" "on" "off"
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with eleven-turbo-v2-5 via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call eleven-turbo-v2-5 (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

text required	string The text to convert into speech.
voice_id	string The ElevenLabs voice ID to use for generation.
output_format	string Enum: "mp3_22050_32" "mp3_24000_48" "mp3_44100_128" "mp3_44100_192" "mp3_44100_32" "mp3_44100_64" "mp3_44100_96" "opus_48000_128" "opus_48000_192" "opus_48000_32" "opus_48000_64" "opus_48000_96" File format of the output (e.g. png, jpeg, mp4).
language_code	string ISO 639-1 language code to enforce.
voice_settings	object
seed	integer [ 0 .. 4294967295 ] Random seed for reproducible results — same seed + inputs gives the same output.
previous_text	string
next_text	string
apply_text_normalization	string Enum: "auto" "on" "off"
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Convert text to speech with eleven-flash-v2-5 via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call eleven-flash-v2-5 (tts). Priced per character — final price scales with text length; min is the smallest possible charge.

Request Body schema: application/json
required

text required	string The text to convert into speech.
voice_id	string The ElevenLabs voice ID to use for generation.
output_format	string Enum: "mp3_22050_32" "mp3_24000_48" "mp3_44100_128" "mp3_44100_192" "mp3_44100_32" "mp3_44100_64" "mp3_44100_96" "opus_48000_128" "opus_48000_192" "opus_48000_32" "opus_48000_64" "opus_48000_96" File format of the output (e.g. png, jpeg, mp4).
language_code	string ISO 639-1 language code to enforce.
voice_settings	object
seed	integer [ 0 .. 4294967295 ] Random seed for reproducible results — same seed + inputs gives the same output.
previous_text	string
next_text	string
apply_text_normalization	string Enum: "auto" "on" "off"
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "Hello from GlianaAI."
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

video-to-video

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate a video from a text prompt or an image.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/wan-2.7-i2v path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "wan-2.7-i2v",
"prompt": "a timelapse of clouds over mountains"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate a video with aleph-2 via x402.

$0.001000–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call aleph-2 (video-to-video). Priced per second ($0.487200/sec) — final price = video length x rate.

Request Body schema: application/json
required

content_moderation	object Settings that affect the behavior of the content moderation system
duration	number >= 0 Duration of the source video in seconds. Used for billing only — not sent to RunwayML. Provide this so the gateway can compute per-second video cost accurately.
keyframes	Array of strings <uri> [ items <uri > ] Timed guidance images placed at specific points in the input video. Each entry has a uri and either seconds (absolute timestamp) or at (fractional position). Up to 5. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
prompt required	string Text prompt describing the edit to apply to the input video
prompt_images	Array of strings <uri> [ items <uri > ] Image keyframes for guiding the edit at specific points in the output video. Up to 5. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
seed	integer [ 0 .. 4294967295 ] Random seed for reproducible results
video_uri required	string HTTPS URL, Runway URI, or data URI of the source video to edit (≤30 seconds) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table",
"video_uri": "https://example.com/input.mp4"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

text

Run any of 90+ generative models pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

One endpoint for the whole catalog: send { model, ...modelInput } — pick any model from GET /v1/models (90+ across image, video, image-to-video, text-to-speech, speech-to-text, music). Responds 402 Payment Required with the per-model price; pay from your own account and retry.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
prompt	string Most models take a text prompt; STT/some take a file/url instead.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-imagine-image",
"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate chat completions with any LLM pay-per-call.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Drop-in for the OpenAI chat completions API: swap the base URL, keep your SDK. Pick any text model from GET /v1/models (category "text"). Billing is a pre-charged ceiling — (estimated input tokens + max_tokens) at the model’s per-1M rates — so set max_tokens to bound spend; the response returns real usage. Supports messages (required), max_tokens, temperature, top_p, stream: true (SSE, OpenAI chunk format), tools/tool_choice (OpenAI function calling — tool_calls + role:"tool" round-trip), and vision (content parts with image_url on vision-capable models). 402 → pay → retry. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

model required	string Text model id (see GET /v1/models, category "text").
required	Array of objects OpenAI-style chat messages: [{ role: "user"\|"assistant"\|"system"\|"tool", content }].
max_tokens	integer Output cap — bounds the pre-charged ceiling. Default 1024.
	Array of objects OpenAI function tools; response returns tool_calls.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "grok-4.3",
"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
],
"max_tokens": 256
}

Run any of 90+ models over a payment channel (pay-as-you-go).

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Open one Tempo channel and pay many calls with off-chain vouchers; settle on close. Non-custodial — the deposit stays in the on-chain escrow.

Request Body schema: application/json
required

model required	string Model id or full run id.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "string"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate text with claude-fable-5 via x402.

$0.053771 per call. Flat price, charged only on success.

Pay-per-call claude-fable-5 (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with claude-opus-4.8 via x402.

$0.026886 per call. Flat price, charged only on success.

Pay-per-call claude-opus-4.8 (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gpt-5.5-pro via x402.

$0.193568 per call. Flat price, charged only on success.

Pay-per-call gpt-5.5-pro (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gpt-5.5 via x402.

$0.032262 per call. Flat price, charged only on success.

Pay-per-call gpt-5.5 (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gemini-3.1-pro via x402.

$0.012905 per call. Flat price, charged only on success.

Pay-per-call gemini-3.1-pro (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with grok-4.3 via x402.

$0.002690 per call. Flat price, charged only on success.

Pay-per-call grok-4.3 (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with minimax-m3 via x402.

$0.001291 per call. Flat price, charged only on success.

Pay-per-call minimax-m3 (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with deepseek-v4-pro via x402.

$0.003744 per call. Flat price, charged only on success.

Pay-per-call deepseek-v4-pro (text).

Request Body schema: application/json
required

messages required	Array of arrays OpenAI-style chat messages: [{ role: "user" \| "system" \| "assistant" \| "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).
max_tokens	integer Output-token cap — bounds the pre-charged price ceiling. Default 1024.
temperature	number Sampling temperature. Passed through where the provider supports it.
top_p	number Nucleus sampling. Passed through where the provider supports it.
stream	boolean true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).
tools	Array of arrays OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.
tool_choice	string "auto" (default) \| "none" \| "required" \| { type: "function", function: { name } }.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with inkling via x402.

$0.005034 per call. Flat price, charged only on success.

Pay-per-call inkling (text).

Request Body schema: application/json
required

messages required	Array of arrays Conversation so far, OpenAI-style: [{ role: "user", content: "..." }]. Roles are system, user and assistant. Send the whole history each call — the API is stateless.
max_tokens required	number >= 0 Maximum tokens to generate. Billed at this ceiling rather than at actual usage, so ask for what you need — an unused allowance is still paid for.
system	string
temperature	number [ 0 .. 1 ]
top_p	number [ 0 .. 1 ]
top_k	number >= 0
stream	boolean
metadata	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
],
"max_tokens": 0
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with inkling-256k via x402.

$0.010068 per call. Flat price, charged only on success.

Pay-per-call inkling-256k (text).

Request Body schema: application/json
required

messages required	Array of arrays Conversation so far, OpenAI-style: [{ role: "user", content: "..." }]. Roles are system, user and assistant. Send the whole history each call — the API is stateless.
max_tokens required	number >= 0 Maximum tokens to generate. Billed at this ceiling rather than at actual usage, so ask for what you need — an unused allowance is still paid for.
system	string
temperature	number [ 0 .. 1 ]
top_p	number [ 0 .. 1 ]
top_k	number >= 0
stream	boolean
metadata	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
],
"max_tokens": 0
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gemini-3.6-flash via x402.

$0.008066 per call. Flat price, charged only on success.

Pay-per-call gemini-3.6-flash (text).

Request Body schema: application/json
required

prompt	string Text prompt, or the model-specific input — see GET /v1/schema?model=.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gemini-3.5-flash-lite via x402.

$0.002689 per call. Flat price, charged only on success.

Pay-per-call gemini-3.5-flash-lite (text).

Request Body schema: application/json
required

prompt	string Text prompt, or the model-specific input — see GET /v1/schema?model=.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a red apple on a table"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with grok-4.5 via x402.

$0.006454 per call. Flat price, charged only on success.

Pay-per-call grok-4.5 (text).

Request Body schema: application/json
required

messages required	Array of arrays Conversation so far, OpenAI-style: [{ role: "user", content: "..." }]. Roles are system, user and assistant. Send the whole history each call — the API is stateless.
max_completion_tokens	any
max_tokens	any
n	any How many outputs to generate.
parallel_tool_calls	any
prompt_cache_key	any
reasoning_effort	any
response_format	any How the result is returned (e.g. a URL or base64 data).
search_parameters	object
seed	any Random seed for reproducible results — same seed + inputs gives the same output.
service_tier	string Enum: "default" "priority"
stream	any
stream_options	object
temperature	any
tool_choice	any
tools	any
top_p	any
user	any Optional end-user identifier for abuse monitoring; not required.
web_search_options	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gpt-5.6-luna via x402.

$0.006453 per call. Flat price, charged only on success.

Pay-per-call gpt-5.6-luna (text).

Request Body schema: application/json
required

input required	any The prompt to send. A plain string for a single turn, or an array of typed content parts for multi-part input.
instructions	string
temperature	number [ 0 .. 2 ]
max_output_tokens	number >= 0
top_p	number [ 0 .. 1 ]
stream	boolean
tools	Array of arrays
tool_choice	any
text	object
reasoning	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"input": "value"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gpt-5.6-terra via x402.

$0.016131 per call. Flat price, charged only on success.

Pay-per-call gpt-5.6-terra (text).

Request Body schema: application/json
required

input required	any The prompt to send. A plain string for a single turn, or an array of typed content parts for multi-part input.
instructions	string
temperature	number [ 0 .. 2 ]
max_output_tokens	number >= 0
top_p	number [ 0 .. 1 ]
stream	boolean
tools	Array of arrays
tool_choice	any
text	object
reasoning	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"input": "value"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with kimi-k3 via x402.

$0.016132 per call. Flat price, charged only on success.

Pay-per-call kimi-k3 (text).

Request Body schema: application/json
required

messages required	Array of arrays Conversation so far, OpenAI-style: [{ role: "user", content: "..." }]. Roles are system, user and assistant. Send the whole history each call — the API is stateless.
temperature	number [ 0 .. 2 ]
max_tokens	number >= 0
max_completion_tokens	number >= 0
top_p	number [ 0 .. 1 ]
frequency_penalty	number [ -2 .. 2 ]
presence_penalty	number [ -2 .. 2 ]
stream	boolean
stream_options	object
tools	Array of arrays
tool_choice	any
response_format	any How the result is returned (e.g. a URL or base64 data).
modalities	Array of arrays
audio	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
]
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with claude-sonnet-5 via x402.

$0.016132 per call. Flat price, charged only on success.

Pay-per-call claude-sonnet-5 (text).

Request Body schema: application/json
required

messages required	Array of arrays Conversation so far, OpenAI-style: [{ role: "user", content: "..." }]. Roles are system, user and assistant. Send the whole history each call — the API is stateless.
max_tokens required	number >= 0 Maximum tokens to generate. Billed at this ceiling rather than at actual usage, so ask for what you need — an unused allowance is still paid for.
system	string
stream	boolean
metadata	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
],
"max_tokens": 0
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with claude-opus-5 via x402.

$0.026886 per call. Flat price, charged only on success.

Pay-per-call claude-opus-5 (text).

Request Body schema: application/json
required

messages required	Array of arrays Conversation so far, OpenAI-style: [{ role: "user", content: "..." }]. Roles are system, user and assistant. Send the whole history each call — the API is stateless.
max_tokens required	number >= 0 Maximum tokens to generate. Billed at this ceiling rather than at actual usage, so ask for what you need — an unused allowance is still paid for.
system	string
stream	boolean
metadata	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"messages": [{"role": "user",
"content": "Summarize x402 in one sentence."
}
],
"max_tokens": 0
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

Generate text with gpt-5.6-sol via x402.

$0.032262 per call. Flat price, charged only on success.

Pay-per-call gpt-5.6-sol (text).

Request Body schema: application/json
required

input required	any The prompt to send. A plain string for a single turn, or an array of typed content parts for multi-part input.
instructions	string
temperature	number [ 0 .. 2 ]
max_output_tokens	number >= 0
top_p	number [ 0 .. 1 ]
stream	boolean
tools	Array of arrays
tool_choice	any
text	object
reasoning	object
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"input": "value"
}

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"output": { }
}

image

Generate an image from a text prompt with any model.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/flux-2-pro-preview path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "flux-2-pro-preview",
"prompt": "a red apple on a wooden table"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

video

Generate a video from a text prompt or an image.

$0.0001–$60 per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Capability endpoint — pick any matching model with GET /v1/models and pass it as { model }. Same pay-per-call charge as /v1/infer (402, then pay and retry); the per-model POST /x402/wan-2.7-i2v path also works.

Request Body schema: application/json
required

model required	string Model id or full run id (see GET /v1/models).
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"model": "wan-2.7-i2v",
"prompt": "a timelapse of clouds over mountains"
}

Response samples

200

Content type

application/json

{"model": "nano-banana-2",
"costMicroUsd": 92400,
"output": {"url": "https://api.glianalabs.com/v1/media/8f2c1d9e4a7b3f60.png",
"contentType": "image/png",
"sizeBytes": 1834127
}
}

Generate a video from text via an image step.

$0.445550 per call. Flat price, charged only on success.

Recipe: text → image → animated video (cheapest path to a video; better subject control). Multi-model pipeline from { prompt }. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
required

prompt required	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark hybrid, 3d meme",
"motionPrompt": "it dances and spins"
}

Generate a video with audio from a text prompt.

$0.844300 per call. Flat price, charged only on success.

Recipe: text → image → video with native AUDIO. Multi-model pipeline from { prompt }. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
required

prompt required	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark hybrid, 3d meme",
"motionPrompt": "it dances and spins"
}

Generate an HD video from text via an image.

$0.470750 per call. Flat price, charged only on success.

Recipe: text → higher-fidelity image → animated video. Multi-model pipeline from { prompt }. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
required

prompt required	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark hybrid, 3d meme",
"motionPrompt": "it dances and spins"
}

Generate a random brainrot character video.

$0.997500 per call. Flat price, charged only on success.

Recipe: random Italian-brainrot character → animated video with audio (also the brainrot-video model). Multi-model pipeline. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
optional

prompt	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"motionPrompt": "it dances and bounces"
}

Run the image-to-video recipe via x402.

$0.445550–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/image-to-video via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark, 3d meme"
}

Run the image-to-video-audio recipe via x402.

$0.844300–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/image-to-video-audio via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a singing cartoon frog"
}

Run the image-to-video-hd recipe via x402.

$0.470750–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/image-to-video-hd via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a crisp product shot of a sneaker"
}

Run the brainrot-video recipe via x402.

$0.997500–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/brainrot-video via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"motionPrompt": "it dances and bounces energetically"
}

utility

Send a JSON-RPC call to a supported chain.

$0.002000 per call. Flat price, charged only on success.

Multi-chain JSON-RPC proxy — { chain, method, params }. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"chain": "base",
"method": "eth_blockNumber",
"params": [ ]
}

Response samples

200

Content type

application/json

{"tool": "tools/rpc",
"costMicroUsd": 2000,
"chain": "base",
"result": "0x1a2b3c"
}

Search the web and return ranked results.

$0.005000 per call. Flat price, charged only on success.

Web search — { q, count?: 1-20, country?: "ID", lang?: "id" }. Returns title, url and snippet per hit, plus which upstream answered. Providers are tried in order, so one being rate-limited falls through rather than failing the call. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"q": "x402 payment protocol",
"count": 5
}

Response samples

200

Content type

application/json

{"tool": "tools/search",
"costMicroUsd": 5000,
"query": "x402 payment protocol",
"provider": "brave",
"count": 2,
"results": [{"title": "x402 — an HTTP-native payment standard",
"url": "https://example.com/x402",
"snippet": "Uses HTTP 402 to attach a USDC payment to any request."
},
{"title": "Paying per API call with x402",
"url": "https://example.com/guide",
"snippet": "A client pays the challenge and retries the same request."
}
]
}

Convert text into embedding vectors.

$0.000500 per call. Flat price, charged only on success.

Text embeddings for search, clustering and RAG — { texts: ["..."] } or { text: "..." }. Up to 100 texts and 32,000 characters per call. Multilingual by default, so Indonesian and English embed into the same space and can be compared directly. Returns the model id and dimensions alongside the vectors. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"texts": ["harga tiket kereta ke Bandung",
"train ticket price to Bandung"
]
}

Response samples

200

Content type

application/json

{"tool": "tools/embed",
"costMicroUsd": 500,
"model": "@cf/baai/bge-m3",
"count": 2,
"dimensions": 1024,
"embeddings": [[0.0121,
-0.0334,
0.0087
],
[0.0118,
-0.0301,
0.0092
]
]
}

Check text for unsafe content categories.

$0.001000 per call. Flat price, charged only on success.

Safety check for user-supplied text — { text }, up to 8,000 characters. Returns flagged plus the guard model hazard categories and its raw verdict. The verdict is that model judgement, not a legal determination: treat it as a signal in your own moderation flow. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "I will find where you live."
}

Response samples

200

Content type

application/json

{"tool": "tools/moderate",
"costMicroUsd": 1000,
"model": "@cf/meta/llama-guard-3-8b",
"flagged": true,
"categories": ["S1"
],
"verdict": "unsafe\nS1",
"chars": 27
}

Fetch spot token prices by ticker symbol.

$0.002000 per call. Flat price, charged only on success.

Spot token prices — { symbols: "BTC,ETH", vs? } (CoinGecko ids also accepted via the same field or { ids }). Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"symbols": "BTC,ETH",
"vs": "usd"
}

Response samples

200

Content type

application/json

{"tool": "tools/token-price",
"costMicroUsd": 2000,
"vs": "USD",
"prices": {"BTC": 68000.12,
"ETH": 3450.5
},
"sources": {"BTC": "coinbase",
"ETH": "coinbase"
}
}

Convert fiat currencies at mid-market rates.

$0.002000 per call. Flat price, charged only on success.

Mid-market fiat exchange rates — { from?: "USD", to?: "IDR,EUR", amount? }. Omit to for every currency. Non-USD pairs are cross-rated via USD; reference rates, not dealable quotes. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"from": "USD",
"to": "IDR,EUR",
"amount": 100
}

Response samples

200

Content type

application/json

{"tool": "tools/exchange-rate",
"costMicroUsd": 2000,
"base": "USD",
"rates": {"IDR": 18076.9467,
"EUR": 0.875576
},
"amount": 100,
"converted": {"IDR": 1807694.6663,
"EUR": 87.5576
},
"as_of": "30 Jul 2026",
"source": "open.er-api.com",
"note": "Mid-market reference rates, not dealable quotes."
}

Parse an Indonesian address into components.

$0.003000 per call. Flat price, charged only on success.

Parse a messy Indonesian address into components — { address }. kabupaten_kota and provinsi are resolved from official Kepmendagri data rather than from a model, so they cannot be invented, and verified reports where the model disagreed. Returns jalan, nomor, rt, rw, kelurahan, kecamatan, kabupaten_kota, provinsi, kode_pos, the official kode with coordinates, and a confidence. kecamatan/kelurahan/kode_pos are as written and unverified. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"address": "Jl. Merdeka No. 12 RT 03/RW 05, Gedong Air, Tanjung Karang Barat, Bandar Lampung 35152"
}

Response samples

200

Content type

application/json

{"tool": "tools/address-id",
"costMicroUsd": 3000,
"input": "Jl. Merdeka No. 12 RT 03/RW 05, Gedong Air, Tanjung Karang Barat, Bandar Lampung 35152",
"parsed": {"jalan": "Merdeka",
"nomor": "12",
"rt": "3",
"rw": "5",
"kelurahan": "Gedong Air",
"kecamatan": "Tanjung Karang Barat",
"kabupaten_kota": "Kota Bandar Lampung",
"provinsi": "Lampung",
"kode_pos": "35152"
},
"wilayah": {"kode": "18.71",
"kabupaten_kota": "Kota Bandar Lampung",
"provinsi": "Lampung",
"lat": -5.42958,
"lng": 105.26257
},
"verified": {"kabupaten_kota": true,
"provinsi": true
},
"confidence": "high",
"notes": [ ]
}

Generate marketplace listing copy from a photo.

$0.008000 per call. Flat price, charged only on success.

Turn a product photo into ready-to-post marketplace copy — { image_url | image_base64 }. Returns title and description in BOTH Indonesian and English, plus category, condition, material, colours and search tags. Written from what is visible only: brands, sizes, materials and warranties are never inferred, and anything the photo does not show is null. Nothing is stored. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry). FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/product.jpg"
}

Response samples

200

Content type

application/json

{"tool": "tools/product-listing",
"costMicroUsd": 8000,
"listing": {"title_id": "Tas Selempang Kulit Coklat Pria",
"title_en": "Men's Brown Leather Crossbody Bag",
"description_id": "Tas selempang berbahan kulit warna coklat. Terdapat tali bahu yang bisa diatur dan satu kompartemen utama dengan ritsleting.",
"description_en": "Brown leather crossbody bag with an adjustable shoulder strap and a single zipped main compartment.",
"category": "Bags & Luggage",
"condition": "new",
"material": "Leather",
"colors": ["coklat",
"brown"
],
"tags": ["tas selempang",
"tas kulit",
"crossbody bag",
"leather bag",
"tas pria"
]
},
"model": "@cf/mistralai/mistral-small-3.1-24b-instruct"
}

Read an ID document into structured JSON.

$0.005000 per call. Flat price, charged only on success.

Read an identity document (Indonesian KTP/SIM/KK/NPWP, foreign passport or driving licence) into structured JSON — { image_url | image_base64 }. Indonesian documents also get structural NIK verification (region code, encoded birth date and gender) as a confidence signal, not proof of authenticity. Nothing is stored, and no face matching is performed. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry). FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/ktp.jpg"
}

Response samples

200

Content type

application/json

{"tool": "tools/ocr-id",
"costMicroUsd": 5000,
"fields": {"document_type": "KTP",
"issuing_country": "INDONESIA",
"id_number": "1871014102900002",
"full_name": "BUDI SANTOSO",
"birth_place": "BANDAR LAMPUNG",
"birth_date": "01-02-1990",
"gender": "PEREMPUAN",
"address": "JL MERDEKA NO 12",
"rt_rw": "003/005",
"village": "GEDONG AIR",
"district": "TANJUNG KARANG BARAT",
"city": null,
"province": null,
"expiry_date": "SEUMUR HIDUP",
"blood_type": "O",
"nationality": "INDONESIA",
"religion": "ISLAM",
"marital_status": "BELUM MENIKAH",
"sim_class": null
},
"verification": {"ok": true,
"format": true,
"region": {"kode": "18.71",
"kabupaten_kota": "Kota Bandar Lampung",
"provinsi": "Lampung"
},
"birth_date": "1990-02-01",
"gender": "P",
"agrees": {"birth_date": true,
"gender": true
},
"notes": [ ]
},
"model": "@cf/mistralai/mistral-small-3.1-24b-instruct"
}

Detect faces with boxes, age and gender.

$0.003000 per call. Flat price, charged only on success.

Detect faces → boxes + score + age/gender, no embeddings — { image_url | image_base64 }. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry). FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/face.jpg"
}

Response samples

200

Content type

application/json

{"tool": "tools/face-detect",
"costMicroUsd": 3000
}

Extract a 512-d embedding for each face.

$0.006000 per call. Flat price, charged only on success.

Detect every face → 512-d ArcFace embedding per face (+ bbox, score, age/gender) — { image_url | image_base64 }. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry). FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/face.jpg"
}

Response samples

200

Content type

application/json

{"tool": "tools/face-embed",
"costMicroUsd": 6000
}

Compare two faces for similarity and match.

$0.011000 per call. Flat price, charged only on success.

Compare two faces → cosine similarity + match — { a:{image_url|image_base64}, b:{image_url|image_base64} }. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry). FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"a": {"image_url": "https://example.com/a.jpg"
},
"b": {"image_url": "https://example.com/b.jpg"
}
}

Response samples

200

Content type

application/json

{"tool": "tools/face-compare",
"costMicroUsd": 11000
}

Read an ID document and match it to a selfie.

$0.015000 per call. Flat price, charged only on success.

Onboarding in one call: read an identity document AND compare the photo on it against a selfie — { id_image:{image_url|image_base64}, selfie:{image_url|image_base64} }. Cheaper than tools/ocr-id plus tools/face-compare separately, and the document is fetched once instead of twice. Returns { document:{fields,verification}, face:{similarity,match,threshold} } — measurements only, NO pass/fail verdict, because the threshold that matters is yours. There is no liveness check, so a photo of a photo can match: treat the result as a signal for your own decision, not proof of identity. Nothing is stored. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry). FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"id_image": {"image_url": "https://example.com/ktp.jpg"
},
"selfie": {"image_url": "https://example.com/selfie.jpg"
}
}

Response samples

200

Content type

application/json

{"tool": "tools/kyc-verify",
"costMicroUsd": 15000,
"document": {"fields": {"document_type": "KTP",
"id_number": "1871014102900002",
"full_name": "BUDI SANTOSO",
"birth_date": "01-02-1990",
"gender": "PEREMPUAN"
},
"verification": {"ok": true,
"region": {"kabupaten_kota": "Kota Bandar Lampung",
"provinsi": "Lampung"
},
"agrees": {"birth_date": true,
"gender": true
}
}
},
"face": {"similarity": 0.87,
"match": true,
"threshold": 0.35
},
"model": "@cf/mistralai/mistral-small-3.1-24b-instruct"
}

Summarize a YouTube video up to 60 minutes.

$0.150000 per call. Flat price, charged only on success.

Summarize a YouTube video (Gemini watches the URL) — { url, style?: bullets|paragraph|chapters, language? }; videos ≤60 min. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"style": "bullets"
}

Response samples

200

Content type

application/json

{"tool": "tools/youtube-summary",
"costMicroUsd": 150000,
"summary": "- The video explains ...\n- It then shows ...",
"video": {"id": "dQw4w9WgXcQ",
"title": "Example video",
"channel": "Example Channel",
"durationSeconds": 212
}
}

Extract typed JSON from a page by schema.

$0.010000 per call. Flat price, charged only on success.

Render a page and return JSON matching a schema you declare — { url, schema, prompt? }. schema is { field: "description" } or { field: { type, description } }, type one of string|number|boolean|string[]. Values are coerced to the declared types; anything the page does not state is null and listed in missing rather than invented. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com/product",
"schema": {"title": "the product name",
"price": {"type": "number",
"description": "listed price"
}
}
}

Response samples

200

Content type

application/json

{"tool": "tools/extract",
"costMicroUsd": 10000,
"url": "https://example.com/product",
"data": {"title": "Widget Pro",
"price": 249000,
"in_stock": true
},
"missing": [ ]
}

Scrape a rendered page to clean markdown.

$0.005000 per call. Flat price, charged only on success.

Render a page (JS) → clean markdown — { url }. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com"
}

Response samples

200

Content type

application/json

{"tool": "tools/scrape",
"costMicroUsd": 5000,
"url": "https://example.com",
"markdown": "# Example\n\nSome page text..."
}

Capture a page screenshot as a hosted PNG.

$0.005000 per call. Flat price, charged only on success.

Capture a page as PNG → hosted URL — { url, fullPage? }. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com"
}

Response samples

200

Content type

application/json

{"tool": "tools/screenshot",
"costMicroUsd": 5000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png",
"source": "https://example.com"
}

Render a branded 1200x630 OG card as a PNG.

$0.020000 per call. Flat price, charged only on success.

Render a 1200×630 branded OG/social card from a title → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"title": "Your headline",
"subtitle": "a short tagline"
}

Response samples

200

Content type

application/json

{"tool": "tools/og-image",
"costMicroUsd": 20000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

Render a 1280x720 YouTube thumbnail as a PNG.

$0.020000 per call. Flat price, charged only on success.

Render a 1280×720 YouTube thumbnail (bold title over an optional background image) → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"title": "I tried this for 30 days",
"subtitle": "the results",
"background": "https://example.com/bg.png"
}

Response samples

200

Content type

application/json

{"tool": "tools/youtube-thumbnail",
"costMicroUsd": 20000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

Render a shareable quote image as a PNG.

$0.020000 per call. Flat price, charged only on success.

Render a 1200×630 shareable quote image → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"quote": "Make it work, make it right, make it fast.",
"author": "Kent Beck"
}

Response samples

200

Content type

application/json

{"tool": "tools/quote-card",
"costMicroUsd": 20000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

Render a code snippet as a dark window PNG.

$0.020000 per call. Flat price, charged only on success.

Render a code snippet as a clean dark window image → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"code": "console.log('hello')",
"title": "app.js"
}

Response samples

200

Content type

application/json

{"tool": "tools/code-image",
"costMicroUsd": 20000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

Render a tweet-style card image as a PNG.

$0.020000 per call. Flat price, charged only on success.

Render a tweet-style card → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "shipping > talking",
"name": "GlianaAI",
"handle": "glianalabs"
}

Response samples

200

Content type

application/json

{"tool": "tools/tweet-image",
"costMicroUsd": 20000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

Render meme text over an image as a PNG.

$0.020000 per call. Flat price, charged only on success.

Top/bottom Impact text over an image → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image": "https://example.com/cat.jpg",
"top": "one does not simply",
"bottom": "make a meme api"
}

Response samples

200

Content type

application/json

{"tool": "tools/meme",
"costMicroUsd": 20000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

Render a social card sized by preset as PNG.

$0.020000 per call. Flat price, charged only on success.

Templated social card sized by preset (og/instagram-square/story/linkedin/podcast) → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"preset": "instagram-square",
"title": "Big news",
"subtitle": "we shipped it"
}

Response samples

200

Content type

application/json

{"tool": "tools/card",
"costMicroUsd": 20000,
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

Scrape a URL title and render an OG card PNG.

$0.030000 per call. Flat price, charged only on success.

Scrape a URL's title + render a branded OG card from it → PNG URL. Utility endpoint (not an AI model) — flat price, paid like /v1/infer (402, then pay and retry).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com"
}

Response samples

200

Content type

application/json

{"tool": "tools/auto-og",
"costMicroUsd": 30000,
"sourceTitle": "Example Domain",
"url": "https://api.glianalabs.com/v1/media/ab12cd34.png"
}

List Indonesian provinces and regencies.

Free — no API key, no payment, no signup.

No charge. Official Indonesian administrative regions — 38 provinsi and 514 kabupaten/kota per Kepmendagri No. 300.2.2-2430 Tahun 2025, with the official kode, capital, centroid, timezone, area and population. Call with ?kode=18 for one region (a provinsi also returns its regencies), ?q=bandung to search by name, ?induk=18 to list one province, or no params for all 38 provinces. Level 1-2 only — kecamatan and desa are not included.

query Parameters

kode	string Official code, e.g. 18 (provinsi) or 18.71 (kabupaten/kota).
q	string Name search; best match first, kota preferred over kabupaten for an ambiguous name.
induk	string Parent provinsi code — lists every kabupaten/kota inside it.
level	string Enum: "provinsi" "kabupaten_kota" Restrict to provinsi or kabupaten_kota.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/tools/wilayah"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"source": "Kepmendagri No. 300.2.2-2430 Tahun 2025 (via github.com/cahyadsn/wilayah)",
"scope": "provinsi + kabupaten/kota (level 1-2)",
"count": 3,
"results": [{"kode": "32.73",
"nama": "Kota Bandung",
"level": "kabupaten_kota",
"induk": "32",
"ibukota": "Bandung",
"lat": -6.92222,
"lng": 107.60694,
"timezone": "WIB",
"utc_offset": 7,
"luas_km2": 167.7,
"penduduk": 2569107
}
]
}

Verify an Indonesian NIK structurally.

Free — no API key, no payment, no signup.

No charge, no model call, instant. Checks an Indonesian NIK (national ID number) against arithmetic: 16-digit format, the region code in digits 1-4 resolved against official Kepmendagri data, and the birth date and gender the number encodes. Pass &birth_date=DD-MM-YYYY and &gender=L|P to cross-check what a user typed against what the number says — that is what catches a transposed digit. Proves consistency, NOT authenticity: a well-formed fabrication passes.

query Parameters

nik required	string 16-digit Indonesian NIK. Spaces are tolerated.
birth_date	string Optional claimed birth date to cross-check, e.g. 01-02-1990.
gender	string Optional claimed gender to cross-check: L/LAKI-LAKI/M/MALE or P/PEREMPUAN/F/FEMALE.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/tools/verify-nik"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"ok": true,
"format": true,
"region": {"kode": "18.71",
"kabupaten_kota": "Kota Bandar Lampung",
"provinsi": "Lampung"
},
"birth_date": "1990-02-01",
"gender": "P",
"agrees": {"birth_date": true,
"gender": true
},
"notes": [ ],
"note": "Structural check only: 16-digit format, the region code against official Kepmendagri data, and the birth date and gender the number encodes. It cannot tell a real NIK from a well-formed fabrication."
}

Convert a number into Indonesian words.

Free — no API key, no payment, no signup.

No charge, no model call. Indonesian number-to-words for the amount-in-words line required on invoices, kwitansi and cheques. Pass ?n=249000 (Indonesian thousands separators accepted). Returns the plain words and the capitalised rupiah phrasing. Whole numbers only — decimals are not spelled.

query Parameters

n

required

string

Whole number, e.g. 249000 or 249.000.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/tools/terbilang"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"number": 249000,
"terbilang": "dua ratus empat puluh sembilan ribu",
"rupiah": "Dua ratus empat puluh sembilan ribu rupiah"
}

Verify an Indonesian tax number structurally.

Free — no API key, no payment, no signup.

No charge, no model call. A 16-digit NPWP is the holder's NIK (since 2024) and gets the full region, birth-date and gender check; the 15-digit legacy form is decomposed into taxpayer id, KPP code and branch code and checked for structure only. Neither proves the number was actually issued — checks says exactly what was tested.

query Parameters

npwp

required

string

15 or 16 digits; dots and dashes ignored.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/tools/verify-npwp"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"ok": true,
"format": "legacy15",
"normalized": "01.234.567.8-901.000",
"parts": {"taxpayer_id": "012345678",
"kpp_code": "901",
"branch_code": "000",
"is_head_office": true
},
"nik": null,
"checks": ["15-digit legacy format: length and structure only"
],
"notes": ["Structure only — the legacy check digit is not verified, so a well-formed number that was never issued will pass."
]
}

Parse a QRIS code and optionally set an amount.

Free — no API key, no payment, no signup.

No charge, no model call. Decodes a QRIS payment code (EMVCo TLV) into merchant name, city, NMID, acquirer, MCC, currency and amount, and reports whether the CRC-16 is intact — valid_crc false means the code is damaged or mistyped and nothing else should be trusted. Add &amount=50000 to also get the same merchant code with that amount set (the standard static-to-dynamic conversion): the merchant account template is preserved byte for byte, the CRC recomputed, and the result re-parsed before it is returned. Does NOT mint a merchant QR — the NMID is issued by an acquirer and is never invented. Test with your acquirer before production use.

query Parameters

payload required	string The QRIS string from the QR code.
amount	string Optional amount to set, e.g. 50000. Refused if the source CRC is invalid.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/tools/qris"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"valid_crc": true,
"crc": {"found": "A1B2",
"computed": "A1B2"
},
"type": "static",
"merchant_name": "WARUNG GLIANA",
"merchant_city": "BANDAR LAMPUNG",
"country": "ID",
"currency": "360",
"amount": null,
"mcc": "5814",
"nmid": "ID1234567890123",
"acquirer": "ID.CO.QRIS.WWW"
}

Get Islamic prayer times for a place and date.

Free — no API key, no payment, no signup.

No charge. Jadwal sholat (imsak, subuh, terbit, dzuhur, ashar, maghrib, isya) computed from solar position. Pass ?city=Bandar Lampung (any Indonesian kabupaten/kota name or kode — the coordinate and timezone come from the official wilayah data) or ?lat=&lng=&tz=. ?days=30 returns a whole month in one call. Methods: kemenag (default, Indonesia), mwl, isna, egypt, makkah, karachi; madhab shafi (default) or hanafi changes ashar only. Calculated times are typically within 1-2 minutes of the official Kemenag table and are not a substitute for a local mosque schedule. Where the sun never reaches the required depression (high latitudes in summer) the affected times are null rather than guessed.

query Parameters

city	string Indonesian kabupaten/kota name or kode. Alternative to lat/lng/tz.
lat	number Latitude, -90..90. Requires lng.
lng	number Longitude, -180..180.
tz	number UTC offset in hours (7 WIB, 8 WITA, 9 WIT). Defaults to the offset implied by lng.
date	string YYYY-MM-DD. Defaults to today in the target timezone.
days	integer [ 1 .. 31 ] Consecutive days to return, 1-31. Default 1.
method	string Enum: "kemenag" "mwl" "isna" "egypt" "makkah" "karachi" Calculation authority.
madhab	string Enum: "shafi" "hanafi" Asr shadow rule.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/tools/prayer-times"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"location": {"kode": "18.71",
"nama": "Kota Bandar Lampung",
"level": "kabupaten_kota",
"induk": "18",
"ibukota": "Bandar Lampung",
"lat": -5.42958,
"lng": 105.26257,
"timezone": "WIB",
"utc_offset": 7
},
"method": {"id": "kemenag",
"label": "Kementerian Agama Republik Indonesia",
"fajr_angle": 20,
"isha": 18,
"ihtiyati": true
},
"madhab": "shafi",
"note": "Calculated from solar position, typically within 1-2 minutes of the official Kemenag table. Not a substitute for your local mosque schedule.",
"date": "2026-07-30",
"times": {"imsak": "04:36",
"fajr": "04:50",
"sunrise": "06:07",
"dhuhr": "12:07",
"asr": "15:30",
"maghrib": "18:04",
"isha": "19:16"
}
}

Run the search tool via x402.

$0.005000 per call. Flat price, charged only on success.

Pay-per-call tools/search via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"q": "x402 payment protocol",
"count": 5
}

Run the embed tool via x402.

$0.000500 per call. Flat price, charged only on success.

Pay-per-call tools/embed via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"texts": ["harga tiket kereta ke Bandung",
"train ticket price to Bandung"
]
}

Run the moderate tool via x402.

$0.001000 per call. Flat price, charged only on success.

Pay-per-call tools/moderate via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "I will find where you live."
}

Detect faces in an image via x402.

$0.003000 per call. Flat price, charged only on success.

Pay-per-call tools/face-detect via x402. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/face.jpg"
}

Extract face embeddings via x402.

$0.006000 per call. Flat price, charged only on success.

Pay-per-call tools/face-embed via x402. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/face.jpg"
}

Compare two face images via x402.

$0.011000 per call. Flat price, charged only on success.

Pay-per-call tools/face-compare via x402. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"a": {"image_url": "https://example.com/a.jpg"
},
"b": {"image_url": "https://example.com/b.jpg"
}
}

Fetch spot token prices via x402.

$0.002000 per call. Flat price, charged only on success.

Pay-per-call tools/token-price via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"symbols": "BTC,ETH",
"vs": "usd"
}

Run the exchange-rate tool via x402.

$0.002000 per call. Flat price, charged only on success.

Pay-per-call tools/exchange-rate via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"from": "USD",
"to": "IDR,EUR",
"amount": 100
}

Run the ocr-id tool via x402.

$0.005000 per call. Flat price, charged only on success.

Pay-per-call tools/ocr-id via x402. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/ktp.jpg"
}

Run the kyc-verify tool via x402.

$0.015000 per call. Flat price, charged only on success.

Pay-per-call tools/kyc-verify via x402. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"id_image": {"image_url": "https://example.com/ktp.jpg"
},
"selfie": {"image_url": "https://example.com/selfie.jpg"
}
}

Run the extract tool via x402.

$0.010000 per call. Flat price, charged only on success.

Pay-per-call tools/extract via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com/product",
"schema": {"title": "the product name",
"price": {"type": "number",
"description": "listed price"
},
"in_stock": {"type": "boolean"
}
}
}

Run the product-listing tool via x402.

$0.008000 per call. Flat price, charged only on success.

Pay-per-call tools/product-listing via x402. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image_url": "https://example.com/product.jpg"
}

Send a JSON-RPC call via x402.

$0.002000 per call. Flat price, charged only on success.

Pay-per-call tools/rpc via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"chain": "base",
"method": "eth_blockNumber",
"params": [ ]
}

Scrape a page to markdown via x402.

$0.005000 per call. Flat price, charged only on success.

Pay-per-call tools/scrape via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com"
}

Capture a page screenshot via x402.

$0.005000 per call. Flat price, charged only on success.

Pay-per-call tools/screenshot via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com"
}

Render an OG social card via x402.

$0.020000 per call. Flat price, charged only on success.

Pay-per-call tools/og-image via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"title": "GlianaAI",
"subtitle": "pay-per-call AI, no signup"
}

Render a YouTube thumbnail via x402.

$0.020000 per call. Flat price, charged only on success.

Pay-per-call tools/youtube-thumbnail via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"title": "I built an AI API",
"subtitle": "in one weekend"
}

Render a quote card image via x402.

$0.020000 per call. Flat price, charged only on success.

Pay-per-call tools/quote-card via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"quote": "Make it work, make it right, make it fast.",
"author": "Kent Beck"
}

Render a code snippet image via x402.

$0.020000 per call. Flat price, charged only on success.

Pay-per-call tools/code-image via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"code": "const x = 42;",
"title": "app.js"
}

Render a tweet-style card via x402.

$0.020000 per call. Flat price, charged only on success.

Pay-per-call tools/tweet-image via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"text": "shipping > talking",
"name": "GlianaAI",
"handle": "glianalabs"
}

Render a meme image via x402.

$0.020000 per call. Flat price, charged only on success.

Pay-per-call tools/meme via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"image": "https://example.com/cat.jpg",
"top": "one does not simply",
"bottom": "ship on friday"
}

Render a social card image via x402.

$0.020000 per call. Flat price, charged only on success.

Pay-per-call tools/card via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"preset": "instagram-square",
"title": "Big news",
"subtitle": "we shipped it"
}

Render an OG card from a URL via x402.

$0.030000 per call. Flat price, charged only on success.

Pay-per-call tools/auto-og via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://example.com"
}

Summarize a YouTube video via x402.

$0.150000 per call. Flat price, charged only on success.

Pay-per-call tools/youtube-summary via x402.

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"style": "bullets"
}

recipe

Generate a video from text via an image step.

$0.445550 per call. Flat price, charged only on success.

Recipe: text → image → animated video (cheapest path to a video; better subject control). Multi-model pipeline from { prompt }. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
required

prompt required	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark hybrid, 3d meme",
"motionPrompt": "it dances and spins"
}

Generate a video with audio from a text prompt.

$0.844300 per call. Flat price, charged only on success.

Recipe: text → image → video with native AUDIO. Multi-model pipeline from { prompt }. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
required

prompt required	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark hybrid, 3d meme",
"motionPrompt": "it dances and spins"
}

Generate an HD video from text via an image.

$0.470750 per call. Flat price, charged only on success.

Recipe: text → higher-fidelity image → animated video. Multi-model pipeline from { prompt }. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
required

prompt required	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark hybrid, 3d meme",
"motionPrompt": "it dances and spins"
}

Generate a random brainrot character video.

$0.997500 per call. Flat price, charged only on success.

Recipe: random Italian-brainrot character → animated video with audio (also the brainrot-video model). Multi-model pipeline. Override steps with { imageModel, videoModel }; { motionPrompt, duration, resolution } tune the video. Price = sum of all steps, charged once (402 → pay → retry) — the advertised amount is the DEFAULT pipeline; model/duration/resolution overrides re-price it. Returns each step's output + the final url.

Request Body schema: application/json
optional

prompt	string Text description of the subject/scene the pipeline should generate.
property name* additional property	any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"motionPrompt": "it dances and bounces"
}

Run the image-to-video recipe via x402.

$0.445550–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/image-to-video via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "an italian-brainrot cat-shark, 3d meme"
}

Run the image-to-video-audio recipe via x402.

$0.844300–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/image-to-video-audio via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a singing cartoon frog"
}

Run the image-to-video-hd recipe via x402.

$0.470750–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/image-to-video-hd via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"prompt": "a crisp product shot of a sneaker"
}

Run the brainrot-video recipe via x402.

$0.997500–$undefined per call, depending on model and input. Exact price is returned in the 402 challenge before you pay, or up front from GET /v1/price?model=.

Pay-per-call recipes/brainrot-video via x402. Price = sum of the pipeline steps; min is the default-configuration price (overriding step models changes it).

Request Body schema: application/json
required

property name*

additional property

any

Responses

Request samples

Payload
cURL
JavaScript

Content type

application/json

{"motionPrompt": "it dances and bounces energetically"
}

Check the prepaid balance behind an API key.

Free — no API key, no payment, no signup.

No charge. Send Authorization: Bearer gk_…. Callers who cannot settle per call from a wallet can instead hold a prepaid balance (topped up in the dashboard) and spend it with an API key; every paid endpoint accepts either. Returns the remaining balance in micro-USD.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/keys/balance"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"account_id": "string",
"balance_micro_usd": 0,
"balance_usd": "string"
}

List all available models with per-call prices.

Free — no API key, no payment, no signup.

No charge — browsing the catalog costs nothing.

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/models"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"models": [{ }
]
}

Get a model's input fields, types and ranges.

Free — no API key, no payment, no signup.

No charge. Pass ?model=. Returns each input field with its type/enum/range and a fileRef flag for file inputs (image/video/audio) — those take a public URL; upload a local file at POST /v1/media.

query Parameters

model

required

string

Model id or full run id (see GET /v1/models).

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/schema"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"model": "string",
"required": ["string"
],
"props": { }
}

Get the exact price of a single model call.

Free — no API key, no payment, no signup.

No charge. Pass ?model= (plus any pricing-relevant fields as query params, e.g. duration/resolution) to get the exact per-call price.

query Parameters

model

required

string

Model id or full run id (see GET /v1/models).

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/price"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"model": "string",
"costMicroUsd": 0,
"unit": "string",
"units": 0
}

Upload a source file and get a hosted URL.

Free — no API key, no payment, no signup.

No charge. Upload a video / image / audio file to use as a model input (e.g. an image-to-video source, or a video-to-video video_uri). Send the raw file as the request body with its Content-Type; max 40 MB. Returns { url } — pass that URL into the model field. Use this when an input is too big for an inline value, or you don't already have a public URL. FILE INPUT: if the image is already on the web or your own storage, pass image_url — we fetch it server-side at datacenter speed, which is the fastest option by far. Sending it inline as image_base64 is simplest and stores nothing anywhere, but base64 adds ~33% to the bytes and you pay your own upload speed, so it is best under ~1MB. For a large local file, upload the RAW bytes to POST /v1/media (free, ≤40MB) and pass the URL: same transfer as base64 minus the 33%, and identity endpoints delete the object as soon as they have read it.

Request Body schema:
video/*
required

Raw file bytes. Content-Type must be video/, image/, or audio/*.

string <binary>

Responses

Request samples

cURL
JavaScript

curl -X POST "https://api.glianalabs.com/v1/media"
# Free — no payment, no key, no signup.

Response samples

200

Content type

application/json

{"url": "http://example.com",
"contentType": "string",
"sizeBytes": 0
}

Fetch a stored media file by its key.

Free — no API key, no payment, no signup.

No charge. Serves an uploaded input or a generated output by the key from its /v1/media URL (32-hex id, optional file extension). Responds with the raw file bytes.

path Parameters

key

required

string^[0-9a-f]{32}(\.[a-z0-9]+)?$

Media key from a /v1/media URL — 32 hex chars, optionally followed by a file extension (e.g. 0f...aa.png).

Responses

Request samples

cURL
JavaScript

curl "https://api.glianalabs.com/v1/media/YOUR_KEY"
# Free — no payment, no key, no signup.

GlianaAI (1)

media

Run any of 90+ generative models pay-per-call.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Run any of 90+ models over a payment channel (pay-as-you-go).

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

image-to-video

Run any of 90+ generative models pay-per-call.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate a video from a text prompt or an image.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Run any of 90+ models over a payment channel (pay-as-you-go).

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate a video with wan-2.7-i2v via x402.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate a video with hh1-i2v via x402.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate a video with hh1.1-i2v via x402.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate a video with hh1.1-r2v via x402.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate a video with hailuo-2.3-fast via x402.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

music

Run any of 90+ generative models pay-per-call.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate music from a text prompt with any model.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Run any of 90+ models over a payment channel (pay-as-you-go).

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate music with music-2.6 via x402.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

Generate music with music-v2 via x402.

Request Body schema: application/jsonrequired

Responses

Request samples

Response samples

stt

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required

Request Body schema: application/json
required