Venice.ai · Schema
ModelResponse
Response schema for model information
CompanyArtificial IntelligenceLLMImage GenerationVideo GenerationText-to-SpeechEmbeddingsPrivacyOpenAI-Compatiblex402
Properties
| Name | Type | Description |
|---|---|---|
| context_length | number | The context length (maximum input tokens) supported by the model. Only present for text models. This is a standard OpenAI-compatible field that mirrors model_spec.availableContextTokens for client com |
| created | number | Release date on Venice API |
| discount_to_user | number | Fractional discount carried by a reseller agreement covering this model, e.g. 0.2 for 20% off, following the OpenRouter convention of publishing a base price alongside a separate discount fraction: us |
| id | string | Model ID |
| model_spec | object | |
| object | string | Object type |
| owned_by | string | Who runs the model |
| type | string | Model type |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/api-evangelist/venice-ai/main/json-schema/venice-ai-model-response-schema.json",
"title": "ModelResponse",
"description": "Response schema for model information",
"x-generated": "2026-10-13",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/venice-ai-openapi.yml#/components/schemas/ModelResponse",
"type": "object",
"properties": {
"context_length": {
"type": "number",
"description": "The context length (maximum input tokens) supported by the model. Only present for text models. This is a standard OpenAI-compatible field that mirrors model_spec.availableContextTokens for client compatibility."
},
"created": {
"type": "number",
"description": "Release date on Venice API"
},
"discount_to_user": {
"type": "number",
"minimum": 0,
"exclusiveMinimum": true,
"maximum": 1,
"exclusiveMaximum": true,
"description": "Fractional discount carried by a reseller agreement covering this model, e.g. 0.2 for 20% off, following the OpenRouter convention of publishing a base price alongside a separate discount fraction: user price = base price × (1 - discount_to_user). Returned only to the reselling partner whose agreement it belongs to, and omitted for every other caller and for models no agreement covers, so an integration should treat an absent field as no discount. Always greater than 0 and less than 1. Prices in model_spec.pricing are what Venice bills and already reflect any promotional discount active for the caller, so apply discount_to_user to those published prices rather than to a separate list rate. Callers buying from Venice directly rather than through a reseller should ignore this field."
},
"id": {
"type": "string",
"description": "Model ID"
},
"model_spec": {
"type": "object",
"properties": {
"availableContextTokens": {
"type": "number",
"description": "The context length supported by the model. Only applicable for text models."
},
"maxCompletionTokens": {
"type": "number",
"description": "The maximum number of completion tokens the model can generate. Use this to know the upper bound for the max_completion_tokens request parameter. Only applicable for text models."
},
"beta": {
"type": "boolean",
"description": "Is this model restricted to beta users only? If true, only users with beta access can use this model"
},
"betaModel": {
"type": "boolean",
"description": "Is this model in beta status?"
},
"privacy": {
"type": "string",
"enum": [
"private",
"anonymized"
],
"description": "The privacy mode of the model. Private models have zero data retention. Anonymized models Venice can not guarantee privacy on, but requests are not affiliated with a user"
},
"regionRestrictions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Country codes where this model is intended to be available. Only present for models with region restrictions metadata."
},
"deprecation": {
"type": "object",
"properties": {
"autoRemap": {
"type": "boolean",
"description": "When true, Venice may automatically remap API requests for this model ID to replacementModelId instead of returning an error."
},
"date": {
"type": "string",
"description": "Legacy ISO 8601 instant aligned with the deprecation sunset used in response headers (`x-venice-model-deprecation-date`). Prefer startsAt / removesAt for new integrations."
},
"removesAt": {
"type": "string",
"description": "ISO 8601 instant when this model ID is omitted from public GET /models listings (same value as `date` today). Consumers should treat the current wall-clock time as past this instant when deciding whether the model remains listed."
},
"replacementModelId": {
"type": "string",
"description": "Suggested public API model ID to migrate to, when one exists."
},
"startsAt": {
"type": "string",
"description": "ISO 8601 instant when deprecation warnings and documentation should be considered active for this model."
}
},
"required": [
"autoRemap",
"date",
"removesAt"
],
"description": "Deprecation information for the model. Only present for models scheduled to be retired"
},
"capabilities": {
"type": "object",
"properties": {
"optimizedForCode": {
"type": "boolean",
"description": "Is the LLM optimized for coding?"
},
"quantization": {
"type": "string",
"enum": [
"fp4",
"fp8",
"fp16",
"bf16",
"int8",
"int4",
"not-available"
],
"description": "The quantization type of the running model."
},
"supportsFunctionCalling": {
"type": "boolean",
"description": "Does the LLM model support function calling?"
},
"supportsAudioInput": {
"type": "boolean",
"description": "Does the LLM support audio input?"
},
"supportsReasoning": {
"type": "boolean",
"description": "Does the model support reasoning with <thinking> blocks of output."
},
"supportsReasoningEffort": {
"type": "boolean",
"description": "Does the model support the reasoning_effort parameter to control reasoning depth."
},
"reasoningEffortOptions": {
"type": "array",
"items": {
"type": "string",
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
},
"description": "Supported reasoning_effort values for this model. Only present when supportsReasoningEffort is true. The \"none\" option means reasoning can be disabled."
},
"defaultReasoningEffort": {
"type": "string",
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"description": "Default reasoning_effort value used when the request does not specify one. Only present when supportsReasoningEffort is true."
},
"supportsResponseSchema": {
"type": "boolean",
"description": "Does the LLM model support response schema? Only models that support function calling can support response_schema."
},
"supportsMultipleImages": {
"type": "boolean",
"description": "Does the LLM support multiple images in a single request? Only applicable when supportsVision is true."
},
"maxImages": {
"type": "number",
"description": "Maximum number of images supported per request. Only present when supportsMultipleImages is true."
},
"maxVideos": {
"type": "number",
"description": "Maximum number of video attachments supported per chat request. Only present when supportsVideoInput is true."
},
"supportsVision": {
"type": "boolean",
"description": "Does the LLM support vision?"
},
"supportsVideoInput": {
"type": "boolean",
"description": "Does the LLM support video input?"
},
"supportsWebSearch": {
"type": "boolean",
"description": "Does the LLM model support web search?"
},
"supportsLogProbs": {
"type": "boolean",
"description": "Does the LLM model support logprobs parameter?"
},
"supportsTeeAttestation": {
"type": "boolean",
"description": "Does the model run inside a Trusted Execution Environment (TEE) with hardware attestation? When true, use GET /tee/attestation and GET /tee/signature to cryptographically verify that inference occurred inside a genuine TEE."
},
"supportsE2EE": {
"type": "boolean",
"description": "Does the model support End-to-End Encryption (E2EE)? When true, clients can encrypt prompts using the TEE public key from attestation, and responses are returned encrypted. Requires supportsTeeAttestation to also be true."
},
"supportsXSearch": {
"type": "boolean",
"description": "Does the model support xAI's native X Search (web + X/Twitter search)? When true, you can use venice_parameters.enable_x_search to activate real-time search powered by xAI."
}
},
"required": [
"optimizedForCode",
"quantization",
"supportsFunctionCalling",
"supportsAudioInput",
"supportsReasoning",
"supportsReasoningEffort",
"supportsResponseSchema",
"supportsMultipleImages",
"supportsVision",
"supportsVideoInput",
"supportsWebSearch",
"supportsLogProbs",
"supportsTeeAttestation",
"supportsE2EE",
"supportsXSearch"
],
"additionalProperties": false,
"description": "Text model specific capabilities."
},
"constraints": {
"anyOf": [
{
"type": "object",
"properties": {
"aspectRatios": {
"type": "array",
"items": {
"type": "string"
},
"description": "Supported aspect ratio options for this model. Only present for models that support aspect ratio selection."
},
"defaultAspectRatio": {
"type": "string",
"description": "The default aspect ratio for this model. Only present for models that support aspect ratio selection."
},
"defaultResolution": {
"type": "string",
"description": "The default resolution for this model. Only present for models that support resolution selection."
},
"resolutions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Supported resolution options for this model. Only present for models that support resolution selection."
},
"defaultQuality": {
"type": "string",
"enum": [
"low",
"medium",
"high"
],
"description": "The default quality for this model. Only present for models that accept the `quality` request parameter (currently GPT Image 2)."
},
"qualities": {
"type": "array",
"items": {
"type": "string",
"enum": [
"low",
"medium",
"high"
]
},
"description": "Supported quality options for this model. Only present for models that accept the `quality` request parameter (currently GPT Image 2)."
},
"promptCharacterLimit": {
"type": "number",
"description": "The maximum supported prompt length."
},
"steps": {
"type": "object",
"properties": {
"default": {
"type": "number",
"description": "The default steps value for the model"
},
"max": {
"type": "number",
"description": "The maximum supported steps value for the model"
}
},
"required": [
"default",
"max"
]
},
"widthHeightDivisor": {
"type": "number",
"description": "The requested width and height of the image generation must be divisible by this value."
},
"maxStyleReferences": {
"type": "number",
"description": "Maximum number of style_references accepted by POST /image/generate. Only present for models that support style references."
},
"supportsStyleReferenceStrength": {
"type": "boolean",
"description": "Whether per-reference `strength` is honored. When false, style_references strength is ignored. Only present for models that support style references."
}
},
"required": [
"promptCharacterLimit",
"steps",
"widthHeightDivisor"
],
"description": "Constraints that apply to image models.",
"title": "Image Model Constraints"
},
{
"type": "object",
"properties": {
"temperature": {
"type": "object",
"properties": {
"default": {
"type": "number",
"description": "The default temperature value for the model"
}
},
"required": [
"default"
]
},
"top_p": {
"type": "object",
"properties": {
"default": {
"type": "number",
"description": "The default top_p value for the model"
}
},
"required": [
"default"
]
},
"frequency_penalty": {
"type": "object",
"properties": {
"default": {
"type": "number",
"description": "The default frequency_penalty value for the model"
}
},
"required": [
"default"
]
},
"presence_penalty": {
"type": "object",
"properties": {
"default": {
"type": "number",
"description": "The default presence_penalty value for the model"
}
},
"required": [
"default"
]
},
"repetition_penalty": {
"type": "object",
"properties": {
"default": {
"type": "number",
"description": "The default repetition_penalty value for the model"
}
},
"required": [
"default"
]
}
},
"required": [
"temperature",
"top_p"
],
"description": "Constraints that apply to text models.",
"title": "Text Model Constraints"
},
{
"type": "object",
"properties": {
"aspect_ratios": {
"type": "array",
"items": {
"type": "string"
},
"description": "The aspect ratios supported by the model. Empty array means the model does not support a defined aspect ratio."
},
"resolutions": {
"type": "array",
"items": {
"type": "string"
},
"description": "The resolutions supported by the model. Empty array means the model does not support a defined resolution."
},
"durations": {
"type": "array",
"items": {
"type": "string"
},
"description": "The durations supported by the model. Empty array means the model does not support a defined duration."
},
"model_type": {
"type": "string",
"enum": [
"image-to-video",
"text-to-video",
"video"
],
"description": "The type of video model."
},
"audio": {
"type": "boolean",
"description": "Does the model support audio generation?"
},
"audio_configurable": {
"type": "boolean",
"description": "Can audio be enabled or disabled for the video generation?"
},
"prompt_character_limit": {
"type": "number",
"description": "The maximum supported prompt length for this video model. If not specified, the default is 2500 characters."
},
"topaz": {
"type": "object",
"properties": {
"models": {
"type": "array",
"items": {
"type": "object",
"properties": {
"display": {
"type": "string"
},
"value": {
"type": "string"
}
},
"required": [
"display",
"value"
]
},
"description": "Available values for the `enhancement_model` request parameter."
},
"sliders": {
"type": "array",
"items": {
"type": "object",
"properties": {
"default": {
"type": "number"
},
"max": {
"type": "number"
},
"min": {
"type": "number"
},
"param": {
"type": "string"
},
"only_for_models": {
"type": "array",
"items": {
"type": "string"
},
"description": "When present, the parameter only applies to these enhancement models."
}
},
"required": [
"default",
"max",
"min",
"param"
]
},
"description": "Numeric enhancement parameters with their valid ranges and defaults."
},
"no_upscale_models": {
"type": "array",
"items": {
"type": "string"
},
"description": "Enhancement models that must run at source resolution (upscale_factor > 1 is rejected with them)."
},
"selects": {
"type": "array",
"items": {
"type": "object",
"properties": {
"default": {
"type": "string"
},
"options": {
"type": "array",
"items": {
"type": "string"
}
},
"param": {
"type": "string"
}
},
"required": [
"default",
"options",
"param"
]
},
"description": "Enum-style enhancement parameters (e.g. `target_fps`, `output_format`, `slowdown_factor`)."
},
"h264_output": {
"type": "boolean",
"description": "Whether the model accepts the `h264_output` parameter."
},
"prompt": {
"type": "boolean",
"description": "Whether the model accepts an optional guidance `prompt` (e.g. Topaz Astra)."
}
},
"description": "Topaz enhancement controls supported by this model. Absent for regular generation models."
}
},
"required": [
"aspect_ratios",
"resolutions",
"durations",
"model_type",
"audio",
"audio_configurable"
],
"description": "Constraints that apply to video models.",
"title": "Video Model Constraints"
},
{
"type": "object",
"properties": {
"aspectRatios": {
"type": "array",
"items": {
"type": "string"
},
"description": "The aspect ratios supported by this model. Omit the parameter to use the model's default setting."
},
"promptCharacterLimit": {
"type": "number",
"description": "The maximum supported prompt length."
},
"combineImages": {
"type": "boolean",
"description": "Whether this model supports combining multiple input images."
},
"maxInputImages": {
"type": "integer",
"minimum": 0,
"exclusiveMinimum": true,
"description": "Maximum number of input images accepted for combine/multi-edit. Absent means the default of 3 (or 1 when combineImages is false)."
},
"singleImageAspectRatio": {
"type": "boolean",
"description": "If false, output dimensions match the input on single-image edits and `aspect_ratio` is ignored. Multi-image edits are unaffected. Defaults to true."
},
"defaultResolution": {
"type": "string",
"description": "The default resolution for this inpaint model. Only present for models that support resolution selection (e.g. GPT Image 2 Edit)."
},
"resolutions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Supported resolution options for this inpaint model. Only present for models that support resolution selection."
},
"defaultQuality": {
"type": "string",
"enum": [
"low",
"medium",
"high"
],
"description": "The default quality for this inpaint model. Only present for models that accept the `quality` request parameter (currently GPT Image 2 Edit)."
},
"qualities": {
"type": "array",
"items": {
"type": "string",
"enum": [
"low",
"medium",
"high"
]
},
"description": "Supported quality options for this inpaint model. Only present for models that accept the `quality` request parameter (currently GPT Image 2 Edit)."
}
},
"required": [
"aspectRatios",
"promptCharacterLimit",
"combineImages"
],
"description": "Constraints that apply to inpaint/edit models.",
"title": "Inpaint Model Constraints"
}
],
"description": "Constraints that apply to this model."
},
"supportsStyleReferences": {
"type": "boolean",
"description": "Whether this image model accepts `style_references` on POST /image/generate. Only present for image models."
},
"description": {
"type": "string",
"description": "A human-readable description of the model and its capabilities."
},
"name": {
"type": "string",
"description": "The name of the model."
},
"modelSource": {
"type": "string",
"description": "The source of the model, such as a URL to the model repository."
},
"offline": {
"type": "boolean",
"default": false,
"description": "Is this model presently offline?"
},
"pricing": {
"anyOf": [
{
"type": "object",
"properties": {
"input": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million input tokens"
},
"diem": {
"type": "number",
"description": "Diem cost per million input tokens"
}
},
"required": [
"usd",
"diem"
]
},
"cache_input": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million cached input tokens (discounted rate for cache reads)"
},
"diem": {
"type": "number",
"description": "Diem cost per million cached input tokens (discounted rate for cache reads)"
}
},
"required": [
"usd",
"diem"
],
"description": "Optional pricing for cached input tokens (cache reads). Only present for models that support context caching."
},
"cache_write": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million cache creation tokens (cache writes). For some providers this may be higher than input price."
},
"diem": {
"type": "number",
"description": "Diem cost per million cache creation tokens (cache writes). For some providers this may be higher than input price."
}
},
"required": [
"usd",
"diem"
],
"description": "Optional pricing for cache creation tokens (cache writes). Only present for models where provider charges for cache writes (e.g., Anthropic charges 1.25x input price)."
},
"output": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million output tokens"
},
"diem": {
"type": "number",
"description": "Diem cost per million output tokens"
}
},
"required": [
"usd",
"diem"
]
},
"extended": {
"type": "object",
"properties": {
"context_token_threshold": {
"type": "number",
"description": "Input token count above which extended pricing applies"
},
"input": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million input tokens (extended tier)"
},
"diem": {
"type": "number",
"description": "Diem cost per million input tokens (extended tier)"
}
},
"required": [
"usd",
"diem"
]
},
"output": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million output tokens (extended tier)"
},
"diem": {
"type": "number",
"description": "Diem cost per million output tokens (extended tier)"
}
},
"required": [
"usd",
"diem"
]
},
"cache_input": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million cached input tokens (extended tier)"
},
"diem": {
"type": "number",
"description": "Diem cost per million cached input tokens (extended tier)"
}
},
"required": [
"usd",
"diem"
]
},
"cache_write": {
"type": "object",
"properties": {
"usd": {
"type": "number",
"description": "USD cost per million cache write tokens (extended tier)"
},
"diem
# --- truncated at 32 KB (59 KB total) ---
# Full source: https://artifacts.apis.io/venice-ai/json-schema/venice-ai-model-response-schema.json
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/venice-ai-model-response"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.