GlianaAI — MPP Grade C
On-chain Activity
Compliance Checks
2 issues
- OpenAPI doc exceeds 64KB limit (121564 bytes)
- Endpoint POST /v1/infer not found
Paid Operations (65)
POST /v1/infer dynamic
Send { model, ...modelInput }. Responds 402 Payment Required with the price; pay from your own account and retry. Price varies per model.
- Amount
- map[currency:USD max:60 min:0.0001 mode:dynamic]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[currency:USD max:60 min:0.0001 mode:dynamic] protocols: [map[mpp:map[currency:0x20C000000000000000000000b9537d11c60E8b50 intent:charge method:tempo]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model id or full run id (see GET /v1/models). |
| prompt | string | Yes | Most models take a text prompt. |
Response Schema (200)
| Field | Type | Description |
|---|---|---|
| costMicroUsd | integer | Amount charged, micro-USD. |
| model | string | - |
| output | object | Model result (media URL or JSON). |
POST /v1/session/infer dynamic
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.
- Amount
- map[currency:USD max:60 min:0.0001 mode:dynamic]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[currency:USD max:60 min:0.0001 mode:dynamic] protocols: [map[mpp:map[currency:0x20C000000000000000000000b9537d11c60E8b50 intent:session method:tempo]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model id or full run id. |
Response Schema (200)
| Field | Type | Description |
|---|---|---|
| costMicroUsd | integer | Amount charged, micro-USD. |
| model | string | - |
| output | object | Model result (media URL or JSON). |
POST /x402/grok-imagine-video-1.5-preview dynamic
Pay-per-call grok-imagine-video-1.5-preview. Priced per second ($0.203000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:1.015000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:1.015000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 |
| duration | integer | No | Length of the output in seconds. |
| image | object | No | Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | No | Text prompt describing what to generate. |
| reference_images | array | No | Reference images that guide characters, style, or composition. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| resolution | string | No |
Output resolution / quality tier.
enum: 480p, 720p |
| size | string | No |
Output dimensions (width × height).
enum: 848x480, 1696x960, 1280x720, 1920x1080 |
| user | string | No | Optional end-user identifier for abuse monitoring; not required. |
| video | object | No | Input video (HTTPS URL or upload) to edit or extend. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/wan-2.7-i2v dynamic
Pay-per-call wan-2.7-i2v. Priced per second ($0.180000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:0.900000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.900000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| duration | integer | No | Length of the output in seconds. |
| image | string | Yes | Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| negative_prompt | string | No | What to avoid in the output. |
| prompt | string | No | Text prompt describing what to generate. |
| resolution | string | No |
Output resolution / quality tier.
enum: 720P, 1080P |
| seed | integer | No | Random seed for reproducible results — same seed + inputs gives the same output. |
| watermark | boolean | No | Whether to add a watermark to the output. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/hh1-i2v dynamic
Pay-per-call hh1-i2v. Priced per second ($0.336000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:1.680000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:1.680000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| duration | integer | No | Length of the output in seconds. |
| image | string | Yes | Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| negative_prompt | string | No | What to avoid in the output. |
| prompt | string | No | Text prompt describing what to generate. |
| resolution | string | No |
Output resolution / quality tier.
enum: 720P, 1080P |
| seed | integer | No | Random seed for reproducible results — same seed + inputs gives the same output. |
| watermark | boolean | No | Whether to add a watermark to the output. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/music-2.6 dynamic
Pay-per-call music-2.6.
- Amount
- map[amount:0.232000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.232000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| bitrate | number | No |
Audio bitrate
enum: 32000, 64000, 128000, 256000 |
| format | string | No |
Audio format
enum: mp3, wav |
| is_instrumental | boolean | No | Generate instrumental music (no vocals) |
| lyrics | string | No | Song lyrics, using \n to separate lines |
| lyrics_optimizer | boolean | No | Automatically generate lyrics based on the prompt description |
| prompt | string | Yes | Description of the music style, mood, and scenario |
| sample_rate | number | No |
Audio sample rate
enum: 16000, 24000, 32000, 44100 |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/grok-stt dynamic
Pay-per-call grok-stt.
- Amount
- map[amount:0.010881 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.010881 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| audio_format | string | No |
Format hint for raw/headerless audio. Required for pcm, mulaw, alaw. Omit for container formats (mp3, wav, etc.) — xAI auto-detects them.
enum: pcm, mulaw, alaw |
| channels | integer | No | Number of audio channels (2–8). Required only for multichannel raw audio; auto-detected for container formats. |
| diarize | boolean | No | When true, enables speaker diarization. Each word in the response includes a `speaker` integer identifying the detected speaker. |
| file | string | No | 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 | No | When true, filler words (uh, um, er) are included in the transcript. Defaults to false — filler words are removed. |
| format | boolean | No | When true, enables Inverse Text Normalization — spoken numbers and currencies are converted to written form (e.g. "one hundred dollars" → "$100"). Requires language to be set. |
| keyterm | array | No | Key terms to bias transcription toward (e.g. product names, proper nouns). Each term up to 50 characters, max 100 terms. Sent as repeated form fields: keyterm=Term+One&keyterm=Term+Two. |
| language | string | No | Language code (e.g. "en", "fr", "de"). Used with format=true to enable Inverse Text Normalization. xAI transcribes in any language regardless — supplying this enables number/currency formatting in the transcript. |
| multichannel | boolean | No | When true, each audio channel is transcribed independently. Results are returned in the `channels` array. Requires channels ≥ 2. |
| sample_rate | integer | No | Sample rate in Hz. Required when audio_format is set. |
| url | string | No | HTTPS URL of an audio file for xAI to fetch server-side. Mutually exclusive with `file` and `websocket`. No gateway-side size limit applies. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| websocket | boolean | No | Enable WebSocket streaming for speech-to-text. When true, establishes a bidirectional WebSocket connection for real-time audio transcription. Mutually exclusive with `file` and `url`. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/gpt-4o-transcribe dynamic
Pay-per-call gpt-4o-transcribe.
- Amount
- map[amount:0.039150 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.039150 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| file | string | Yes | 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 | No | The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. |
| prompt | string | No | An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. |
| temperature | number | No | 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. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/universal-3-pro dynamic
Pay-per-call universal-3-pro.
- Amount
- map[amount:0.022839 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.022839 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| audio_end_at | integer | No | Timestamp (in milliseconds) to end transcription at. |
| audio_start_from | integer | No | Timestamp (in milliseconds) to start transcription from. |
| audio_url | string | Yes | 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 | No | Enable automatic chapter detection. |
| auto_highlights | boolean | No | Enable automatic extraction of key phrases and highlights. |
| boost_param | string | No |
How much to boost the words in word_boost.
enum: low, default, high |
| content_safety | boolean | No | Enable content safety detection for sensitive content. |
| custom_spelling | array | No | Custom spelling rules to replace specific words or phrases in the transcription output. |
| disfluencies | boolean | No | Include filler words like "um", "uh", etc. in the transcript. |
| domain | string | No |
Domain-specific transcription mode. "medical-v1" enables medical terminology optimization.
enum: medical-v1 |
| dual_channel | boolean | No | Process audio as dual-channel (stereo) for better accuracy. |
| entity_detection | boolean | No | Enable detection of entities like names, organizations, and locations. |
| filter_profanity | boolean | No | Filter profanity from the transcription. |
| iab_categories | boolean | No | Enable IAB (Interactive Advertising Bureau) content taxonomy classification. |
| keyterms_prompt | array | No | 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 | No | The language code for the audio file (e.g., "en", "es", "fr"). Defaults to automatic language detection. |
| language_detection | boolean | No | Enable automatic language detection. When enabled with speech_models, the system will automatically select the best model for the detected language. |
| multichannel | boolean | No | Process each audio channel separately for multi-channel audio files. |
| prompt | string | No | A custom prompt to guide transcription style, formatting, and output characteristics. Maximum 1,500 words. |
| redact_pii | boolean | No | Redact personally identifiable information. |
| redact_pii_audio | boolean | No | Generate a redacted audio file with PII removed. |
| redact_pii_policies | array | No | Specific PII policies to apply for redaction. |
| redact_pii_sub | string | No |
Strategy for substituting redacted PII.
enum: entity_name, hash |
| sentiment_analysis | boolean | No | Enable sentiment analysis for each sentence. |
| speaker_labels | boolean | No | Enable speaker diarization to identify different speakers in the audio. |
| speakers_expected | integer | No | Expected number of speakers for speaker diarization. |
| speech_threshold | number | No | Confidence threshold for speech detection. |
| temperature | number | No | Controls randomness in model output (0.0-1.0). Lower values make output more deterministic. Default is 0.0. |
| webhook_url | string | No | URL to receive webhook notifications when transcription is complete. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| websocket | boolean | No | Enable real-time WebSocket streaming for live audio transcription. When true, a WebSocket connection is established instead of submitting a pre-recorded transcription job. Cannot be used with audio_url. |
| word_boost | array | No | Array of words to boost recognition accuracy (legacy - use keyterms_prompt instead). |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/flux-2-pro-preview dynamic
Pay-per-call flux-2-pro-preview.
- Amount
- map[amount:0.054000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.054000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| height | integer | No | Height of the generated image in pixels (minimum 64). Omit to let BFL pick. |
| input_images | array | No | 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 | No |
Output image format. Defaults to jpeg.
enum: jpeg, png, webp |
| prompt | string | Yes | Text prompt for image generation or editing. |
| safety_tolerance | integer | No | Tolerance for input/output moderation. 0 is the strictest, 5 the most permissive. Defaults to 2. |
| seed | integer | No | Optional seed for reproducible generation. |
| width | integer | No | Width of the generated image in pixels (minimum 64). Omit to let BFL pick. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/flux-2-max dynamic
Pay-per-call flux-2-max.
- Amount
- map[amount:0.126000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.126000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| height | integer | No | Height of the generated image in pixels (minimum 64). Omit to let BFL pick. |
| input_images | array | No | Up to 8 reference images for editing or multi-image composition. Each entry is an HTTPS URL or a data:image/...;base64,... URI. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| output_format | string | No |
Output image format. Defaults to jpeg.
enum: jpeg, png, webp |
| prompt | string | Yes | Text prompt for image generation or editing. |
| safety_tolerance | integer | No | Tolerance for input/output moderation. 0 is the strictest, 5 the most permissive. Defaults to 2. |
| seed | integer | No | Optional seed for reproducible generation. |
| width | integer | No | Width of the generated image in pixels (minimum 64). Omit to let BFL pick. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/flux-2-flex dynamic
Pay-per-call flux-2-flex.
- Amount
- map[amount:0.090000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.090000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| guidance | number | No | Classifier-free guidance scale (1.5–10). Higher values follow the prompt more strictly at the cost of realism. |
| height | integer | No | Height of the generated image in pixels (minimum 64). Omit to let BFL pick. |
| input_images | array | No | 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 | No |
Output image format. Defaults to jpeg.
enum: jpeg, png, webp |
| prompt | string | Yes | Text prompt for image generation or editing. |
| prompt_upsampling | boolean | No | Whether BFL should expand short prompts before generation. Defaults to true on flex. |
| safety_tolerance | integer | No | Tolerance for input/output moderation. 0 is the strictest, 5 the most permissive. Defaults to 2. |
| seed | integer | No | Optional seed for reproducible generation. |
| steps | integer | No | Number of denoising steps (1–50). Higher steps yield more detail at the cost of latency. |
| width | integer | No | Width of the generated image in pixels (minimum 64). Omit to let BFL pick. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/grok-imagine-image-quality dynamic
Pay-per-call grok-imagine-image-quality.
- Amount
- map[amount:0.072500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.072500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: 1:1, 3:4, 4:3, 9:16, 16:9, 2:3, 3:2, 9:19.5, 19.5:9, 9:20, 20:9, 1:2, 2:1, auto |
| image | object | No | Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| images | array | No | Reference images to guide generation. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| mask | object | No | Mask image marking the region to edit (inpaint). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| n | integer | No | How many outputs to generate. |
| prompt | string | Yes | Text prompt describing what to generate. |
| quality | string | No |
Output quality level.
enum: low, medium, high |
| resolution | string | No |
Output resolution / quality tier.
enum: 1k, 2k |
| response_format | string | No |
How the result is returned (e.g. a URL or base64 data).
enum: url, b64_json |
| user | string | No | Optional end-user identifier for abuse monitoring; not required. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/grok-imagine-image dynamic
Pay-per-call grok-imagine-image.
- Amount
- map[amount:0.029000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.029000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
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 |
| image | object | No | 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 | No | 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 | No | 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 | No | How many outputs to generate. |
| prompt | string | Yes | Text prompt describing what to generate. |
| quality | string | No |
Output quality level.
enum: low, medium, high |
| resolution | string | No |
Output resolution / quality tier.
enum: 1k, 2k |
| response_format | string | No |
How the result is returned (e.g. a URL or base64 data).
enum: url, b64_json |
| user | string | No | Optional end-user identifier for abuse monitoring; not required. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-pro dynamic
Pay-per-call recraftv4-pro.
- Amount
- map[amount:0.543750 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.543750 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-vector dynamic
Pay-per-call recraftv4-vector.
- Amount
- map[amount:0.174000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.174000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-pro-vector dynamic
Pay-per-call recraftv4-pro-vector.
- Amount
- map[amount:0.652500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.652500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1-vector dynamic
Pay-per-call recraftv4-1-vector.
- Amount
- map[amount:0.174000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.174000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1-utility-vector dynamic
Pay-per-call recraftv4-1-utility-vector.
- Amount
- map[amount:0.174000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.174000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1-utility-pro dynamic
Pay-per-call recraftv4-1-utility-pro.
- Amount
- map[amount:0.543750 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.543750 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1-utility-pro-vector dynamic
Pay-per-call recraftv4-1-utility-pro-vector.
- Amount
- map[amount:0.652500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.652500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1-pro-vector dynamic
Pay-per-call recraftv4-1-pro-vector.
- Amount
- map[amount:0.652500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.652500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1-utility dynamic
Pay-per-call recraftv4-1-utility.
- Amount
- map[amount:0.087000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.087000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1 dynamic
Pay-per-call recraftv4-1.
- Amount
- map[amount:0.087000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.087000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4-1-pro dynamic
Pay-per-call recraftv4-1-pro.
- Amount
- map[amount:0.543750 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.543750 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv4 dynamic
Pay-per-call recraftv4.
- Amount
- map[amount:0.087000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.087000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/recraftv3 dynamic
Pay-per-call recraftv3.
- Amount
- map[amount:0.087000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.087000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| controls | object | No | Advanced generation controls (style, color, and artistic settings). |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
| style | string | No | Visual style preset to apply. |
| substyle | string | No | A finer style variant within the chosen style. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/gpt-image-2 dynamic
Pay-per-call gpt-image-2.
- Amount
- map[amount:0.058000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.058000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| background | string | No |
Background transparency setting. Use transparent for images with no background, opaque for a solid background, or auto to let the model decide.
enum: transparent, opaque, auto |
| images | array | No | 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 | No |
Output format for the generated image
enum: png, webp, jpeg |
| prompt | string | Yes | Text prompt describing the image to generate or edit |
| quality | string | No |
Quality of the generated image
enum: low, medium, high, auto |
| size | string | No |
Size of the generated image
enum: 1024x1024, 1024x1536, 1536x1024, auto |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/gpt-image-1.5 dynamic
Pay-per-call gpt-image-1.5.
- Amount
- map[amount:0.058000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.058000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| images | array | No | Input images for image editing, 1-16 entries. Each entry is base64-encoded (raw string or data:image/{png|jpeg|webp};base64,... URI). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | Yes | Text prompt describing the image to generate or edit |
| quality | string | No |
Quality of the generated image
enum: low, medium, high, auto |
| size | string | No |
Size of the generated image
enum: 256x256, 512x512, 1024x1024, 1792x1024, 1024x1792 |
| style | string | No |
Style of the generated image
enum: vivid, natural |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/nano-banana-pro dynamic
Pay-per-call nano-banana-pro.
- Amount
- map[amount:0.224750 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.224750 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
| image_input | array | No | 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 | No |
Output image dimensions.
enum: 1K, 2K, 4K |
| output_format | string | No |
File format of the output (e.g. png, jpeg, mp4).
enum: jpg, png, webp |
| prompt | string | Yes | Text prompt describing what to generate. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/nano-banana dynamic
Pay-per-call nano-banana.
- Amount
- map[amount:0.056550 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.056550 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
| image_input | array | No | Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| image_size | string | No |
Output image dimensions.
enum: 1K, 2K, 4K |
| output_format | string | No |
File format of the output (e.g. png, jpeg, mp4).
enum: jpg, png, webp |
| prompt | string | Yes | Text prompt describing what to generate. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/nano-banana-2 dynamic
Pay-per-call nano-banana-2.
- Amount
- map[amount:0.111650 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.111650 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: match_input_image, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
| google_search | boolean | No | Allow the model to use Google Search for grounding. |
| image_input | array | No | 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 | No | Allow the model to search for reference images. |
| output_format | string | No |
File format of the output (e.g. png, jpeg, mp4).
enum: jpg, png |
| prompt | string | Yes | Text prompt describing what to generate. |
| resolution | string | No |
Output resolution / quality tier.
enum: 1K, 2K, 4K |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/imagen-4 dynamic
Pay-per-call imagen-4.
- Amount
- map[amount:0.087000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.087000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Aspect ratio of the generated image
enum: 1:1, 3:4, 4:3, 9:16, 16:9 |
| person_generation | string | No |
Allow the model to generate images of people. dont_allow: block people, allow_adult: adults only, allow_all: adults and children
enum: dont_allow, allow_adult, allow_all |
| prompt | string | Yes | Text prompt describing the image to generate |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/seedream-4.5 dynamic
Pay-per-call seedream-4.5.
- Amount
- map[amount:0.087000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.087000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: match_input_image, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 |
| disable_safety_checker | boolean | No | Turn off the safety filter on outputs. |
| image_input | array | No | 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 | No | Maximum number of images to return. |
| prompt | string | Yes | Text prompt describing what to generate. |
| sequential_image_generation | string | No |
Generate a sequence of related images.
enum: disabled, auto |
| size | string | No |
Output dimensions (width × height).
enum: 2K, 4K |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/seedream-5-lite dynamic
Pay-per-call seedream-5-lite.
- Amount
- map[amount:0.076125 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.076125 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: match_input_image, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 |
| image_input | array | No | Reference image(s) to guide generation (HTTPS URL or upload). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| max_images | integer | No | Maximum number of images to return. |
| output_format | string | No |
File format of the output (e.g. png, jpeg, mp4).
enum: png, jpeg |
| prompt | string | Yes | Text prompt describing what to generate. |
| sequential_image_generation | string | No |
Generate a sequence of related images.
enum: disabled, auto |
| size | string | No |
Output dimensions (width × height).
enum: 2K, 3K |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/seedream-4.0 dynamic
Pay-per-call seedream-4.0.
- Amount
- map[amount:0.065250 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.065250 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: match_input_image, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 |
| enhance_prompt | boolean | No | Let the model automatically expand/improve your prompt. |
| height | integer | No | Output height in pixels. |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No |
Output dimensions (width × height).
enum: 1K, 2K, 4K, custom |
| width | integer | No | Output width in pixels. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/wan-2.6-image dynamic
Pay-per-call wan-2.6-image.
- Amount
- map[amount:0.054000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.054000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| negative_prompt | string | No | What to avoid in the output. |
| prompt | string | Yes | Text prompt describing what to generate. |
| size | string | No | Output dimensions (width × height). |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/grok-tts dynamic
Pay-per-call grok-tts. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.017000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.017000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| language | string | Yes | 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 | No |
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.
enum: 0, 1 |
| output_format | object | No | Output audio format. Defaults to MP3 at 24 kHz / 128 kbps when omitted. |
| speed | number | No | Speech speed multiplier. 1.0 is normal speed. Range: 0.7 to 1.5. Defaults to 1.0. Only used in WebSocket mode. |
| text | string | No | Text to convert to speech. Maximum 15,000 characters. Supports inline speech tags: [pause], [laugh], <whisper>…</whisper>, etc. Required for REST mode, mutually exclusive with websocket. |
| text_normalization | boolean | No | When true, normalizes written-form text into spoken-form before synthesis (e.g. "Dr." → "Doctor", "100" → "one hundred"). Defaults to false. |
| voice_id | string | No | 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. |
| websocket | boolean | No | Enable WebSocket streaming for text-to-speech. When true, establishes a bidirectional WebSocket connection. Mutually exclusive with text. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/tts-1-hd dynamic
Pay-per-call tts-1-hd. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.033000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.033000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| response_format | string | No |
The output format for the audio. Supported formats are mp3, opus, wav, aac and flac.
enum: mp3, opus, wav, aac, flac |
| speed | number | No | The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default. |
| text | string | Yes | The text to generate audio for. Maximum length is 4096 characters. |
| voice | string | No |
The voice to use when generating the audio. Defaults to alloy.
enum: alloy, echo, fable, onyx, nova, shimmer |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/tts-1 dynamic
Pay-per-call tts-1. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.017000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.017000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| response_format | string | No |
The output format for the audio. Supported formats are mp3, opus, wav, aac and flac.
enum: mp3, opus, wav, aac, flac |
| speed | number | No | The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default. |
| text | string | Yes | The text to generate audio for. Maximum length is 4096 characters. |
| voice | string | No |
The voice to use when generating the audio. Defaults to alloy.
enum: alloy, echo, fable, onyx, nova, shimmer |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/speech-2.8-turbo dynamic
Pay-per-call speech-2.8-turbo. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.065500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.065500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| emotion | string | No |
Emotion control for synthesized speech
enum: happy, sad, angry, fearful, disgusted, surprised, calm, fluent |
| format | string | No |
Output audio format
enum: mp3, flac, wav |
| pitch | integer | No | Pitch adjustment (-12 to 12) |
| sample_rate | number | No |
Audio sample rate
enum: 8000, 16000, 22050, 24000, 32000, 44100 |
| speed | number | No | Speech speed (0.5 to 2) |
| text | string | Yes | The text to convert to speech. Maximum 10,000 characters. |
| voice_id | string | No | The voice ID to use for synthesis |
| volume | number | No | Speech volume (0 to 10) |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/speech-2.8-hd dynamic
Pay-per-call speech-2.8-hd. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.109000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.109000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| emotion | string | No |
Emotion control for synthesized speech
enum: happy, sad, angry, fearful, disgusted, surprised, calm, fluent |
| format | string | No |
Output audio format
enum: mp3, flac, wav |
| pitch | integer | No | Pitch adjustment (-12 to 12) |
| sample_rate | number | No |
Audio sample rate
enum: 8000, 16000, 22050, 24000, 32000, 44100 |
| speed | number | No | Speech speed (0.5 to 2) |
| text | string | Yes | The text to convert to speech. Maximum 10,000 characters. |
| voice_id | string | No | The voice ID to use for synthesis |
| volume | number | No | Speech volume (0 to 10) |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/tts-2 dynamic
Pay-per-call tts-2. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.038000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.038000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| apply_text_normalization | boolean | No | When enabled, text normalization expands numbers, dates, times, and abbreviations before converting to speech. Turning this off may reduce latency. |
| bit_rate | integer | No | Bits per second of the audio. Only for compressed audio formats (mp3, opus). The default is 128,000. |
| output_format | string | No |
The output format for the audio. Supported formats are mp3, opus, wav, and flac. Defaults to mp3.
enum: mp3, opus, wav, flac |
| sample_rate | integer | No | The synthesis sample rate in hertz. Accepts: 8000, 16000, 22050, 24000, 32000, 44100, 48000. The default is 48,000. |
| speaking_rate | number | No | 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 | No | 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 | string | Yes | The text to be synthesized into speech. Maximum input of 2,000 characters. |
| timestamp_type | string | No |
Controls timestamp metadata returned with the audio. "word" returns word-level timing, "character" returns character-level timing. Note: adds latency. Defaults to none.
enum: none, word, character |
| voice_id | string | No |
The ID of the voice to use for synthesizing speech. Defaults to Dennis.
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 |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/tts-1.5-max dynamic
Pay-per-call tts-1.5-max. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.038000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.038000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| apply_text_normalization | boolean | No | When enabled, text normalization expands numbers, dates, times, and abbreviations before converting to speech. Turning this off may reduce latency. |
| bit_rate | integer | No | Bits per second of the audio. Only for compressed audio formats (mp3, opus). The default is 128,000. |
| output_format | string | No |
The output format for the audio. Supported formats are mp3, opus, wav, and flac. Defaults to mp3.
enum: mp3, opus, wav, flac |
| sample_rate | integer | No | The synthesis sample rate in hertz. Accepts: 8000, 16000, 22050, 24000, 32000, 44100, 48000. The default is 48,000. |
| speaking_rate | number | No | 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 | No | 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 | string | Yes | The text to be synthesized into speech. Maximum input of 2,000 characters. |
| timestamp_type | string | No |
Controls timestamp metadata returned with the audio. "word" returns word-level timing, "character" returns character-level timing. Note: adds latency. Defaults to none.
enum: none, word, character |
| voice_id | string | No |
The ID of the voice to use for synthesizing speech. Defaults to Dennis.
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 |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/tts-1.5-mini dynamic
Pay-per-call tts-1.5-mini. Priced per character; the amount shown is an example — final scales with text length.
- Amount
- map[amount:0.028000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.028000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| apply_text_normalization | boolean | No | When enabled, text normalization expands numbers, dates, times, and abbreviations before converting to speech. Turning this off may reduce latency. |
| bit_rate | integer | No | Bits per second of the audio. Only for compressed audio formats (mp3, opus). The default is 128,000. |
| output_format | string | No |
The output format for the audio. Supported formats are mp3, opus, wav, and flac. Defaults to mp3.
enum: mp3, opus, wav, flac |
| sample_rate | integer | No | The synthesis sample rate in hertz. Accepts: 8000, 16000, 22050, 24000, 32000, 44100, 48000. The default is 48,000. |
| speaking_rate | number | No | 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 | No | 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 | string | Yes | The text to be synthesized into speech. Maximum input of 2,000 characters. |
| timestamp_type | string | No |
Controls timestamp metadata returned with the audio. "word" returns word-level timing, "character" returns character-level timing. Note: adds latency. Defaults to none.
enum: none, word, character |
| voice_id | string | No |
The ID of the voice to use for synthesizing speech. Defaults to Dennis.
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 |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/gemini-3.1-flash-tts dynamic
Pay-per-call gemini-3.1-flash-tts.
- Amount
- map[amount:0.017400 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.017400 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| maxOutputTokens | integer | No | Maximum number of tokens to generate |
| stopSequences | array | No | Sequences where the model will stop generating further tokens |
| temperature | number | No | Controls randomness in generation (0-2) |
| text | string | Yes | The text to convert to speech. Maximum 10,000 characters. |
| topK | integer | No | Only sample from the top K tokens. Smaller K = more focused, larger K = more diverse |
| topP | number | No | Nucleus sampling threshold (0-1). Tokens with cumulative probability up to topP are considered |
| voice | string | No |
The voice to use for speech synthesis
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 |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/grok-imagine-video dynamic
Pay-per-call grok-imagine-video. Priced per second ($0.101500/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:0.507500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.507500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Output aspect ratio (e.g. 16:9, 1:1, 9:16).
enum: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 |
| duration | integer | No | Length of the output in seconds. |
| image | object | No | Input image (HTTPS URL or upload) to guide or edit from. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | No | Text prompt describing what to generate. |
| reference_images | array | No | Reference images that guide characters, style, or composition. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| resolution | string | No |
Output resolution / quality tier.
enum: 480p, 720p |
| size | string | No |
Output dimensions (width × height).
enum: 848x480, 1696x960, 1280x720, 1920x1080 |
| user | string | No | Optional end-user identifier for abuse monitoring; not required. |
| video | object | No | Input video (HTTPS URL or upload) to edit or extend. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/q3-pro dynamic
Pay-per-call q3-pro. Priced per second ($0.217500/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:1.087500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:1.087500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio (text-to-video only). Default: 16:9
enum: 16:9, 9:16, 3:4, 4:3, 1:1 |
| audio | boolean | No | Enable audio-video synchronization. Default: true for Q3 models. When false, outputs silent video |
| duration | integer | No | Video duration in seconds (1-16) |
| end_image | string | No | End image for start/end-to-video generation. Must be used together with start_image. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | No | Text prompt describing what should appear in the video |
| resolution | string | No |
Video resolution
enum: 540p, 720p, 1080p |
| start_image | string | No | Start image for video generation. Use alone for image-to-video, or with end_image for start/end-to-video. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/q3-turbo dynamic
Pay-per-call q3-turbo. Priced per second ($0.101500/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:0.507500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.507500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio (text-to-video only). Default: 16:9
enum: 16:9, 9:16, 3:4, 4:3, 1:1 |
| audio | boolean | No | Enable audio-video synchronization. Default: true for Q3 models. When false, outputs silent video |
| duration | integer | No | Video duration in seconds (1-16) |
| end_image | string | No | End image for start/end-to-video generation. Must be used together with start_image. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | No | Text prompt describing what should appear in the video |
| resolution | string | No |
Video resolution
enum: 540p, 720p, 1080p |
| start_image | string | No | Start image for video generation. Use alone for image-to-video, or with end_image for start/end-to-video. Accepts public URL or Base64 data URI (data:image/png;base64,...) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/gen-4.5 dynamic
Pay-per-call gen-4.5. Priced per second ($0.261000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:1.305000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:1.305000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| content_moderation | object | No | Content moderation settings |
| duration | integer | No | Video duration in seconds |
| image_input | string | No | HTTPS URL, Runway URI, or data URI containing an image for image-to-video Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | Yes | Text prompt describing what should appear in the video |
| ratio | string | No |
Resolution/aspect ratio of the output video
enum: 1280:720, 720:1280, 1104:832, 960:960, 832:1104, 1584:672 |
| seed | integer | No | Random seed for reproducible results |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/aleph-2 dynamic
Pay-per-call aleph-2. Priced per second ($0.487200/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:2.436000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:2.436000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| content_moderation | object | No | Settings that affect the behavior of the content moderation system |
| duration | number | No | Duration of the source video in seconds. Used for billing only — not sent to RunwayML. Provide this so the gateway can compute per-second video cost accurately. |
| keyframes | array | No | Timed guidance images placed at specific points in the input video. Each entry has a uri and either seconds (absolute timestamp) or at (fractional position). Up to 5. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | Yes | Text prompt describing the edit to apply to the input video |
| prompt_images | array | No | Image keyframes for guiding the edit at specific points in the output video. Up to 5. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| seed | integer | No | Random seed for reproducible results |
| video_uri | string | Yes | HTTPS URL, Runway URI, or data URI of the source video to edit (≤30 seconds) Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/v6 dynamic
Pay-per-call v6. Priced per second ($0.166750/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:0.833750 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.833750 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio
enum: 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9 |
| duration | integer | No | Video duration in seconds (1 to 15) |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image_input | string | No | Base64-encoded reference image for image-to-video generation (data:image/...;base64,...). The image will be uploaded to Pixverse automatically. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| negative_prompt | string | No | Negative text prompt |
| prompt | string | Yes | Text prompt describing the video to generate |
| quality | string | No |
Video quality
enum: 360p, 540p, 720p, 1080p |
| seed | integer | No | Random seed for reproducibility |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/v5.6 dynamic
Pay-per-call v5.6. Priced per second ($0.217500/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:1.087500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:1.087500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio
enum: 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9 |
| duration | number | No |
Video duration in seconds
enum: 5, 8, 10 |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image_input | string | No | Base64-encoded reference image for image-to-video generation (data:image/...;base64,...). The image will be uploaded to Pixverse automatically. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| motion_mode | string | No |
Motion mode (fast only available when duration=5; 1080p does not support fast)
enum: normal, fast |
| negative_prompt | string | No | Negative text prompt |
| prompt | string | Yes | Text prompt describing the video to generate |
| quality | string | No |
Video quality
enum: 360p, 540p, 720p, 1080p |
| seed | integer | No | Random seed for reproducibility |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/hailuo-2.3-fast dynamic
Pay-per-call hailuo-2.3-fast. Priced per second ($0.079750/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:0.398750 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.398750 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| duration | number | No |
Length of the output in seconds.
enum: 6, 10 |
| fast_pretreatment | boolean | No | Faster input pre-processing (may trade a little quality for speed). |
| first_frame_image | string | Yes | URL or base64 data URI of the first frame image Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | No | Text prompt describing what to generate. |
| prompt_optimizer | boolean | No | Let the model automatically optimize your prompt. |
| resolution | string | No |
Output resolution / quality tier.
enum: 768P, 1080P |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/hailuo-2.3 dynamic
Pay-per-call hailuo-2.3. Priced per second ($0.118418/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:0.592090 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.592090 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| duration | number | No |
Length of the output in seconds.
enum: 6, 10 |
| fast_pretreatment | boolean | No | Faster input pre-processing (may trade a little quality for speed). |
| first_frame_image | string | No | Image to use as the first frame of the video. |
| prompt | string | No | Text prompt describing what to generate. |
| prompt_optimizer | boolean | No | Let the model automatically optimize your prompt. |
| resolution | string | No |
Output resolution / quality tier.
enum: 768P, 1080P |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/veo-3.1-fast dynamic
Pay-per-call veo-3.1-fast. Priced per second ($0.435000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:2.175000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:2.175000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio
enum: 16:9, 9:16, 1:1 |
| duration | string | No |
Video duration
enum: 4s, 6s, 8s |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image_input | string | No | Base64-encoded reference image for i2v Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | Yes | Text prompt describing the video to generate |
| resolution | string | No |
Video resolution
enum: 720p, 1080p |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/veo-3-fast dynamic
Pay-per-call veo-3-fast. Priced per second ($0.435000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:2.175000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:2.175000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio
enum: 16:9, 9:16, 1:1 |
| duration | string | No |
Video duration
enum: 4s, 6s, 8s |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image_input | string | No | Base64-encoded reference image for i2v Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | Yes | Text prompt describing the video to generate |
| resolution | string | No |
Video resolution
enum: 720p, 1080p |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/veo-3.1 dynamic
Pay-per-call veo-3.1. Priced per second ($0.870000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:4.350000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:4.350000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio
enum: 16:9, 9:16, 1:1 |
| duration | string | No |
Video duration
enum: 4s, 6s, 8s |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image_input | string | No | Base64-encoded reference image for i2v Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | Yes | Text prompt describing the video to generate |
| resolution | string | No |
Video resolution
enum: 720p, 1080p |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/veo-3 dynamic
Pay-per-call veo-3. Priced per second ($0.580000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:2.900000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:2.900000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio
enum: 16:9, 9:16, 1:1 |
| duration | string | No |
Video duration
enum: 4s, 6s, 8s |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image_input | string | No | Base64-encoded reference image for i2v Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| prompt | string | Yes | Text prompt describing the video to generate |
| resolution | string | No |
Video resolution
enum: 720p, 1080p |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/seedance-2.0-fast dynamic
Pay-per-call seedance-2.0-fast. Priced per second ($0.246500/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:1.232500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:1.232500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio. Ignored if an image is used.
enum: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21 |
| camera_fixed | boolean | No | Whether to fix camera position |
| duration | integer | No | Video duration in seconds |
| fps | number | No | Frame rate (frames per second) |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image | string | No | 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 | No | 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 | string | Yes | Text prompt describing the video to generate |
| reference_images | array | No | 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 | No | 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 | No |
Video resolution
enum: 480p, 720p |
| seed | integer | No | Random seed for reproducible generation |
| watermark | boolean | No | Whether to add a watermark to the output video |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/seedance-2.0 dynamic
Pay-per-call seedance-2.0. Priced per second ($0.797500/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:3.987500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:3.987500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | No |
Video aspect ratio. Ignored if an image is used.
enum: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21 |
| camera_fixed | boolean | No | Whether to fix camera position |
| duration | integer | No | Video duration in seconds |
| fps | number | No | Frame rate (frames per second) |
| generate_audio | boolean | No | Whether to generate audio with the video |
| image | string | No | 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 | No | 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 | string | Yes | Text prompt describing the video to generate |
| reference_images | array | No | 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 | No | 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 | No |
Video resolution
enum: 480p, 720p, 1080p |
| seed | integer | No | Random seed for reproducible generation |
| watermark | boolean | No | Whether to add a watermark to the output video |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/hh1-t2v dynamic
Pay-per-call hh1-t2v. Priced per second ($0.336000/sec); the amount shown is a 5s example — final = video length × rate.
- Amount
- map[amount:1.680000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:1.680000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| duration | integer | No | Length of the output in seconds. |
| prompt | string | Yes | Text prompt describing what to generate. |
| ratio | string | No |
Output aspect ratio.
enum: 16:9, 9:16, 1:1, 4:3, 3:4 |
| resolution | string | No |
Output resolution / quality tier.
enum: 720P, 1080P |
| seed | integer | No | Random seed for reproducible results — same seed + inputs gives the same output. |
| watermark | boolean | No | Whether to add a watermark to the output. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/krea-2-medium-turbo dynamic
Pay-per-call krea-2-medium-turbo.
- Amount
- map[amount:0.021750 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.021750 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | Yes |
Aspect ratio of the generated image.
enum: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16 |
| complexity | integer | No | K2 Complexity slider (-100 to 100). 0 disables the slider LoRA. |
| creativity | string | No |
Prompt expansion mode. `raw` disables expansion; `low`, `medium`, `high` control strength. Does not affect the K2 Intensity, Complexity, or Movement slider LoRAs.
enum: raw, low, medium, high |
| image_style_references | array | No | 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 | No | K2 Intensity slider (-100 to 100). 0 disables the slider LoRA. |
| moodboards | array | No | Moodboard references (currently limited to one). |
| movement | integer | No | K2 Movement slider (-100 to 100). 0 disables the slider LoRA. |
| prompt | string | Yes | Text prompt describing the image to generate. |
| resolution | string | Yes |
Resolution scale.
enum: 1K |
| seed | No | Random seed for reproducible generations. Pass null or omit for a random seed. | |
| styles | array | No | Styles (typically LoRAs) to apply to the generation. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/krea-2-medium dynamic
Pay-per-call krea-2-medium.
- Amount
- map[amount:0.043500 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.043500 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | Yes |
Aspect ratio of the generated image.
enum: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16 |
| complexity | integer | No | K2 Complexity slider (-100 to 100). 0 disables the slider LoRA. |
| creativity | string | No |
Prompt expansion mode. `raw` disables expansion; `low`, `medium`, `high` control strength. Does not affect the K2 Intensity, Complexity, or Movement slider LoRAs.
enum: raw, low, medium, high |
| image_style_references | array | No | Reference images to drive the visual style (up to 10). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url. |
| intensity | integer | No | K2 Intensity slider (-100 to 100). 0 disables the slider LoRA. |
| moodboards | array | No | Moodboard references (currently limited to one). |
| movement | integer | No | K2 Movement slider (-100 to 100). 0 disables the slider LoRA. |
| prompt | string | Yes | Text prompt describing the image to generate. |
| resolution | string | Yes |
Resolution scale.
enum: 1K |
| seed | No | Random seed for reproducible generations. Pass null or omit for a random seed. | |
| styles | array | No | Styles (typically LoRAs) to apply to the generation. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
POST /x402/krea-2-large dynamic
Pay-per-call krea-2-large.
- Amount
- map[amount:0.087000 currency:USD mode:fixed]
- Currency
- -
- Method
- Intent
- -
- 402 Declared
- Yes
price: map[amount:0.087000 currency:USD mode:fixed] protocols: [map[x402:map[]]]
Input Schema
| Field | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | Yes |
Aspect ratio of the generated image.
enum: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16 |
| complexity | integer | No | K2 Complexity slider (-100 to 100). 0 disables the slider LoRA. |
| creativity | string | No |
Prompt expansion mode. `raw` disables expansion; `low`, `medium`, `high` control strength. Does not affect the K2 Intensity, Complexity, or Movement slider LoRAs.
enum: raw, low, medium, high |
| image_style_references | array | No | 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 | No | K2 Intensity slider (-100 to 100). 0 disables the slider LoRA. |
| moodboards | array | No | Moodboard references (currently limited to one). |
| movement | integer | No | K2 Movement slider (-100 to 100). 0 disables the slider LoRA. |
| prompt | string | Yes | Text prompt describing the image to generate. |
| resolution | string | Yes |
Resolution scale.
enum: 1K |
| seed | No | Random seed for reproducible generations. Pass null or omit for a random seed. | |
| styles | array | No | Styles (typically LoRAs) to apply to the generation. |
Response Schema (200)
{
"$ref": "#/components/schemas/InferOutput"
}
Payment Methods
- Methods
- -
- Intents
- -
- Currencies (discovery)
- -
- Multiple Challenges
- No
Security
- TLS Version
- TLSv1.3
- Challenge ID Unique
- -
- Challenge ID Length
- -
- Digest Binding
- -
Uptime
- Discovery
- Reachable (146ms)
- Challenge
- Reachable (126ms)
- Last Checked
Schema Completeness
- Paid Operations
- 65
- With Input Schema
- 65
- With Description
- 65
Documentation
- Homepage
- https://ai.glianalabs.com
- API Reference
- https://ai.glianalabs.com/docs
- llms.txt
- -
Discovery
- OpenAPI URL
- https://api.glianalabs.com/openapi.json
- OpenAPI Version
- 3.1.0
- Service Version
- 1
- Document Size
- 121564 bytes
- Document Hash
- 42dc2529618cb0f097634a55109ced577d0f76c76516b784671ba2ab0a326688
Version History (7 snapshots)
- removed endpoint: POST /x402/p-image
- new endpoint: POST /x402/p-image
- removed endpoint: POST /x402/p-image
- removed endpoint: POST /x402/p-image-edit
- removed endpoint: POST /x402/p-image-try-on
- removed endpoint: POST /x402/p-image-upscale
- removed endpoint: POST /x402/p-video
- removed endpoint: POST /x402/p-video-animate
- removed endpoint: POST /x402/p-video-avatar
- removed endpoint: POST /x402/p-video-replace
- new endpoint: POST /x402/p-image
- new endpoint: POST /x402/p-image-edit
- new endpoint: POST /x402/p-image-try-on
- new endpoint: POST /x402/p-image-upscale
- new endpoint: POST /x402/p-video
- new endpoint: POST /x402/p-video-animate
- new endpoint: POST /x402/p-video-avatar
- new endpoint: POST /x402/p-video-replace
- removed endpoint: POST /x402/p-image
- removed endpoint: POST /x402/p-image-edit
- removed endpoint: POST /x402/p-image-try-on
- removed endpoint: POST /x402/p-image-upscale
- removed endpoint: POST /x402/p-video
- removed endpoint: POST /x402/p-video-animate
- removed endpoint: POST /x402/p-video-avatar
- removed endpoint: POST /x402/p-video-replace
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- new endpoint: POST /x402/p-image
- new endpoint: POST /x402/p-image-edit
- new endpoint: POST /x402/p-image-try-on
- new endpoint: POST /x402/p-image-upscale
- new endpoint: POST /x402/p-video
- new endpoint: POST /x402/p-video-animate
- new endpoint: POST /x402/p-video-avatar
- new endpoint: POST /x402/p-video-replace
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- new endpoint: POST /x402/krea-2-large
- new endpoint: POST /x402/krea-2-medium
- new endpoint: POST /x402/krea-2-medium-turbo
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- new endpoint: POST /x402/aleph-2
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
- document hash changed (no semantic differences detected)
Scan snapshots
| Date | Grade | Score | Response | Status |
|---|---|---|---|---|
| 2026-06-14 | C | 67% | 754ms | Up |
| 2026-06-15 | C | 64% | 114ms | Up |
| 2026-06-16 | C | 64% | 139ms | Up |
| 2026-06-17 | C | 64% | 510ms | Up |
| 2026-06-18 | C | 64% | 405ms | Up |
| 2026-06-19 | C | 64% | 1023ms | Up |
| 2026-06-20 | C | 64% | 125ms | Up |