Venice API Docs: /models

Postman Collection

For additional examples, please see this Postman Collection.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

type

Filter models by type. Use "all" to get all model types.

Available options:

asr,

embedding,

image,

text,

tts,

upscale,

inpaint,

video

Example:

"text"

Response

data

object[]

required

List of available models

Show child attributes

data.id

string

required

Model ID

Example:

"venice-uncensored"

data.model_spec

object

required

Show child attributes

data.model_spec.availableContextTokens

number

The context length supported by the model. Only applicable for text models.

Example:

32768

data.model_spec.beta

boolean

Is this model in beta?

Example:

false

data.model_spec.privacy

enum<string>

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

Available options:

private,

anonymized

Example:

"private"

data.model_spec.capabilities

object

Text model specific capabilities.

Show child attributes

data.model_spec.capabilities.optimizedForCode

boolean

required

Is the LLM optimized for coding?

Example:

true

data.model_spec.capabilities.quantization

enum<string>

required

The quantization type of the running model.

Available options:

fp4,

fp8,

fp16,

bf16,

int8,

int4,

not-available

Example:

"fp8"

data.model_spec.capabilities.supportsFunctionCalling

boolean

required

Does the LLM model support function calling?

Example:

true

data.model_spec.capabilities.supportsReasoning

boolean

required

Does the model support reasoning with blocks of output.

Example:

true

data.model_spec.capabilities.supportsResponseSchema

boolean

required

Does the LLM model support response schema? Only models that support function calling can support response_schema.

Example:

true

data.model_spec.capabilities.supportsVision

boolean

required

Does the LLM support vision?

Example:

true

data.model_spec.capabilities.supportsWebSearch

boolean

required

Does the LLM model support web search?

Example:

true

data.model_spec.capabilities.supportsLogProbs

boolean

required

Does the LLM model support logprobs parameter?

Example:

true

data.model_spec.constraints

Image Model Constraints · object

Constraints that apply to this model.

Image Model Constraints
Text Model Constraints
Video Model Constraints

Show child attributes

data.model_spec.constraints.promptCharacterLimit

number

required

The maximum supported prompt length.

Example:

2048

data.model_spec.constraints.steps

object

required

Show child attributes

data.model_spec.constraints.steps.default

number

required

The default steps value for the model

Example:

25

data.model_spec.constraints.steps.max

number

required

The maximum supported steps value for the model

Example:

50

data.model_spec.constraints.widthHeightDivisor

number

required

The requested width and height of the image generation must be divisible by this value.

Example:

8

data.model_spec.name

string

The name of the model.

Example:

"Venice Uncensored 1.1"

data.model_spec.modelSource

string

The source of the model, such as a URL to the model repository.

Example:

"https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition"

data.model_spec.offline

boolean

default:false

Is this model presently offline?

Example:

false

data.model_spec.pricing

LLM Model Pricing · object

Pricing details for the model

LLM Model Pricing
Image Model Pricing
Audio Model Pricing

Show child attributes

data.model_spec.pricing.input

object

required

Show child attributes

data.model_spec.pricing.input.usd

number

required

USD cost per million input tokens

Example:

0.7

data.model_spec.pricing.input.diem

number

required

Diem cost per million input tokens

Example:

7

data.model_spec.pricing.output

object

required

Show child attributes

data.model_spec.pricing.output.usd

number

required

USD cost per million output tokens

Example:

2.8

data.model_spec.pricing.output.diem

number

required

Diem cost per million output tokens

Example:

28

data.model_spec.traits

string[]

Traits that apply to this model. You can specify a trait to auto-select a model vs. specifying the model ID in your request to avoid breakage as Venice updates and iterates on its models.

Example:

["default_code"]

data.model_spec.voices

string[]

The voices available for this TTS model. Only applicable for TTS models.

Example:

[
  "af_alloy",
  "af_aoede",
  "af_bella",
  "af_heart",
  "af_jadzia"
]

data.object

enum<string>

required

Object type

Available options:

model

Example:

"model"

data.owned_by

enum<string>

required

Who runs the model

Available options:

venice.ai

Example:

"venice.ai"

data.type

enum<string>

required

Model type

Available options:

asr,

embedding,

image,

text,

tts,

upscale,

inpaint,

video

Example:

"text"

data.created

number

Release date on Venice API

Example:

1699000000

object

enum<string>

required

Available options:

list

type

required

Type of models returned.

Available options:

asr,

embedding,

image,

text,

tts,

upscale,

inpaint,

video

Example:

"text"

Venice APIs

List Models

Postman Collection

Authorizations

Query Parameters

Response

Venice APIs

​Postman Collection

Authorizations

Query Parameters

Response

Postman Collection