Public models - Cerebras Inference

curl -sS 'https://api.cerebras.ai/public/v1/models' | jq

{
  "object": "list",
  "data": [
    {
      "id": "gpt-oss-120b",
      "object": "model",
      "created": 1754438400,
      "owned_by": "OpenAI",
      "name": "OpenAI GPT OSS",
      "description": "This model excels at efficient reasoning across science, math, and coding applications. It's ideal for real-time coding assistance, processing large documents for Q&A and summarization, agentic research workflows, and regulated on-premises workloads.",
      "hugging_face_id": "openai/gpt-oss-120b",
      "pricing": {
        "prompt": "0.00000035",
        "completion": "0.00000075"
      },
      "capabilities": {
        "streaming": true,
        "function_calling": true,
        "structured_outputs": true,
        "vision": false,
        "json_mode": true,
        "tools": true,
        "tool_choice": true,
        "parallel_tool_calls": false,
        "response_format": true,
        "reasoning": true
      },
      "supported_parameters": {
        "temperature": true,
        "top_p": true,
        "seed": true,
        "stop": true,
        "max_completion_tokens": true,
        "logprobs": true,
        "top_logprobs": true,
        "frequency_penalty": true,
        "presence_penalty": true,
        "logit_bias": true,
        "repetition_penalty": false
      },
      "architecture": {
        "modality": "text",
        "tokenizer": "GPT",
        "instruct_type": "harmony"
      },
      "limits": {
        "max_context_length": 131072,
        "max_completion_tokens": 40960,
        "requests_per_minute": null,
        "tokens_per_minute": null
      },
      "datacenter_locations": [],
      "deprecated": false,
      "preview": false,
      "quantization": "FP16/8 (weights only)"
    }
  ]
}

GET

public

models

curl -sS 'https://api.cerebras.ai/public/v1/models' | jq

{
  "object": "list",
  "data": [
    {
      "id": "gpt-oss-120b",
      "object": "model",
      "created": 1754438400,
      "owned_by": "OpenAI",
      "name": "OpenAI GPT OSS",
      "description": "This model excels at efficient reasoning across science, math, and coding applications. It's ideal for real-time coding assistance, processing large documents for Q&A and summarization, agentic research workflows, and regulated on-premises workloads.",
      "hugging_face_id": "openai/gpt-oss-120b",
      "pricing": {
        "prompt": "0.00000035",
        "completion": "0.00000075"
      },
      "capabilities": {
        "streaming": true,
        "function_calling": true,
        "structured_outputs": true,
        "vision": false,
        "json_mode": true,
        "tools": true,
        "tool_choice": true,
        "parallel_tool_calls": false,
        "response_format": true,
        "reasoning": true
      },
      "supported_parameters": {
        "temperature": true,
        "top_p": true,
        "seed": true,
        "stop": true,
        "max_completion_tokens": true,
        "logprobs": true,
        "top_logprobs": true,
        "frequency_penalty": true,
        "presence_penalty": true,
        "logit_bias": true,
        "repetition_penalty": false
      },
      "architecture": {
        "modality": "text",
        "tokenizer": "GPT",
        "instruct_type": "harmony"
      },
      "limits": {
        "max_context_length": 131072,
        "max_completion_tokens": 40960,
        "requests_per_minute": null,
        "tokens_per_minute": null
      },
      "datacenter_locations": [],
      "deprecated": false,
      "preview": false,
      "quantization": "FP16/8 (weights only)"
    }
  ]
}

Retrieve details about publicly available Cerebras models without an API key, including context length, pricing, and supported features. This endpoint supports multiple response formats for compatibility with different platforms.

This endpoint is public and does not require an API key.

Supported Formats

The endpoint supports three response formats via the format query parameter:

Default (Cerebras) - Native Cerebras format
OpenRouter - OpenRouter-compatible format
HuggingFace - HuggingFace-compatible format

Query Parameters

format

string

Response format. Options: openrouter, huggingface. Omit for default Cerebras format.

Response

Default Format

object

string

The object type, which is always list for list responses or model for single model responses.

data

array

Array of model objects (only in list responses).

Show model properties

string

The model identifier (e.g., gpt-oss-120b).

object

string

The object type, which is always model.

created

integer

The Unix timestamp (in seconds) of when the model was created.

owned_by

string

The organization that owns the model.

name

string

Human-readable model name.

description

string

Description of the model’s capabilities and recommended use cases.

hugging_face_id

string

The HuggingFace repository identifier for this model.

pricing

object

Pricing per token in USD.

Show pricing fields

prompt

string

Cost per prompt token.

completion

string

Cost per completion token.

capabilities

object

Boolean flags for supported features.

Show capability fields

streaming

boolean

Whether streaming is supported.

function_calling

boolean

Whether function calling is supported.

structured_outputs

boolean

Whether structured outputs are supported.

vision

boolean

Whether vision/image input is supported.

json_mode

boolean

Whether JSON mode is supported.

tools

boolean

Whether tool use is supported.

tool_choice

boolean

Whether tool choice is supported.

parallel_tool_calls

boolean

Whether parallel tool calls are supported.

response_format

boolean

Whether response format control is supported.

reasoning

boolean

Whether the model supports reasoning.

supported_parameters

object

Boolean flags for supported API parameters.

architecture

object

Model architecture details.

Show architecture fields

modality

string

Input/output modality (e.g., text).

tokenizer

string

Tokenizer type.

instruct_type

string

Instruction tuning format.

limits

object

Model limits.

Show limit fields

max_context_length

integer

Maximum context window in tokens.

max_completion_tokens

integer

Maximum completion tokens.

requests_per_minute

integer

Requests per minute limit (null if unlimited).

tokens_per_minute

integer

Tokens per minute limit (null if unlimited).

deprecated

boolean

Whether this model is deprecated.

preview

boolean

Whether this model is in preview.

quantization

string

Quantization method used for the model.

OpenRouter Format

data

array

Array of model objects with extended metadata.

Show extended properties

string

The model identifier.

hugging_face_id

string

The HuggingFace repository identifier.

name

string

Human-readable model name.

input_modalities

array

Supported input types (e.g., ["text"]).

output_modalities

array

Supported output types (e.g., ["text"]).

context_length

integer

Maximum context window size in tokens.

max_output_length

integer

Maximum output length in tokens.

pricing

object

Pricing information per token.

Show pricing fields

prompt

string

Cost per prompt token.

completion

string

Cost per completion token.

request

string

Cost per request (typically "0").

image

string

Cost per image token (typically "0" for text-only models).

input_cache_read

string

Cost per cached input token read (typically "0").

input_cache_write

string

Cost per cached input token write (typically "0").

supported_sampling_parameters

array

List of supported sampling parameters.

supported_features

array

List of supported features (e.g., ["tools", "json_mode", "structured_outputs"]).

HuggingFace Format

data

array

Array of model objects.

Show properties

string

The model identifier.

hugging_face_id

string

The HuggingFace repository identifier.

object

string

The object type, which is always model.

created

integer

The Unix timestamp (in seconds) of when the model was created.

owned_by

string

The organization that owns the model.

pricing

object

Pricing in USD per million tokens.

Show pricing fields

input

number

Price per million input tokens.

output

number

Price per million output tokens.

context_length

integer

Maximum context window size in tokens.

capabilities

object

Boolean flags for supported features.

curl -sS 'https://api.cerebras.ai/public/v1/models' | jq

{
  "object": "list",
  "data": [
    {
      "id": "gpt-oss-120b",
      "object": "model",
      "created": 1754438400,
      "owned_by": "OpenAI",
      "name": "OpenAI GPT OSS",
      "description": "This model excels at efficient reasoning across science, math, and coding applications. It's ideal for real-time coding assistance, processing large documents for Q&A and summarization, agentic research workflows, and regulated on-premises workloads.",
      "hugging_face_id": "openai/gpt-oss-120b",
      "pricing": {
        "prompt": "0.00000035",
        "completion": "0.00000075"
      },
      "capabilities": {
        "streaming": true,
        "function_calling": true,
        "structured_outputs": true,
        "vision": false,
        "json_mode": true,
        "tools": true,
        "tool_choice": true,
        "parallel_tool_calls": false,
        "response_format": true,
        "reasoning": true
      },
      "supported_parameters": {
        "temperature": true,
        "top_p": true,
        "seed": true,
        "stop": true,
        "max_completion_tokens": true,
        "logprobs": true,
        "top_logprobs": true,
        "frequency_penalty": true,
        "presence_penalty": true,
        "logit_bias": true,
        "repetition_penalty": false
      },
      "architecture": {
        "modality": "text",
        "tokenizer": "GPT",
        "instruct_type": "harmony"
      },
      "limits": {
        "max_context_length": 131072,
        "max_completion_tokens": 40960,
        "requests_per_minute": null,
        "tokens_per_minute": null
      },
      "datacenter_locations": [],
      "deprecated": false,
      "preview": false,
      "quantization": "FP16/8 (weights only)"
    }
  ]
}

Retrieve Specific Model

You can also retrieve information about a specific model by appending the model ID to the endpoint:

GET https://api.cerebras.ai/public/v1/models/{model_id}

Path Parameters

model_id

string

required

The ID of the model to retrieve (e.g., gpt-oss-120b, zai-glm-4.7).

curl -sS 'https://api.cerebras.ai/public/v1/models/gpt-oss-120b' | jq

{
  "id": "gpt-oss-120b",
  "object": "model",
  "created": 1754438400,
  "owned_by": "OpenAI",
  "name": "OpenAI GPT OSS",
  "description": "This model excels at efficient reasoning across science, math, and coding applications. It's ideal for real-time coding assistance, processing large documents for Q&A and summarization, agentic research workflows, and regulated on-premises workloads.",
  "hugging_face_id": "openai/gpt-oss-120b",
  "pricing": {
    "prompt": "0.00000035",
    "completion": "0.00000075"
  },
  "capabilities": {
    "streaming": true,
    "function_calling": true,
    "structured_outputs": true,
    "vision": false,
    "json_mode": true,
    "tools": true,
    "tool_choice": true,
    "parallel_tool_calls": false,
    "response_format": true,
    "reasoning": true
  },
  "limits": {
    "max_context_length": 131072,
    "max_completion_tokens": 40960,
    "requests_per_minute": null,
    "tokens_per_minute": null
  },
  "deprecated": false,
  "preview": false,
  "quantization": "FP16/8 (weights only)"
}

Use Cases

Platform Integration - Use the OpenRouter or HuggingFace formats to integrate Cerebras models into existing platforms that support these standards. Model Discovery - Programmatically discover available models and their capabilities without authentication. Pricing Comparison - Compare pricing across different models using the structured pricing information. Feature Detection - Check which features (streaming, tools, JSON mode) are supported by each model.

Retrieve model

Create batch

⌘I

​Supported Formats

​Query Parameters

​Response

​Default Format

​OpenRouter Format

​HuggingFace Format

​Retrieve Specific Model

​Path Parameters

​Use Cases

Supported Formats

Query Parameters

Response

Default Format

OpenRouter Format

HuggingFace Format

Retrieve Specific Model

Path Parameters

Use Cases