Skip to main content
GET
/
v1
/
models
List Available Models
curl --request GET \
  --url https://api.incredible.one/v1/models

​
Response Format

The endpoint returns a JSON object following the OpenRouter API schema with a data array containing model metadata.

​
Response Structure

{
  "data": [
    {
      "id": "string",
      "canonical_slug": "string",
      "hugging_face_id": "string",
      "name": "string",
      "created": "number (Unix timestamp)",
      "description": "string",
      "context_length": "number",
      "architecture": {
        "modality": "string",
        "input_modalities": ["string"],
        "output_modalities": ["string"],
        "tokenizer": "string",
        "instruct_type": "string | null"
      },
      "pricing": {
        "prompt": "string (USD per token)",
        "completion": "string (USD per token)",
        "request": "string (USD per request)",
        "image": "string (USD per image)",
        "web_search": "string (USD per search)",
        "internal_reasoning": "string (USD per reasoning token)"
      },
      "top_provider": {
        "context_length": "number",
        "max_completion_tokens": "number | null",
        "is_moderated": "boolean"
      },
      "per_request_limits": "object | null",
      "supported_parameters": ["string"],
      "default_parameters": {
        "temperature": "number | null",
        "top_p": "number | null",
        "frequency_penalty": "number | null"
      }
    }
  ]
}

​
Available Models

​
small-2

Model ID: small-2 Incredible’s small-2 model finishes complex work across all your tools—no supervision required.
  • Context Length: 200,000 tokens
  • Tokenizer: Minimax
  • Modality: text→text
  • Pricing:
    • Prompt: $0.0008 per token
    • Completion: $0.0045 per token
  • Supported Parameters: tools, response_format

​
small-1

Model ID: small-1 Incredible’s small-1 model is aimed for accurately handling complex tool-chaining with large context.
  • Context Length: 200,000 tokens
  • Tokenizer: GLM
  • Modality: text→text
  • Pricing:
    • Prompt: $0.001 per token
    • Completion: $0.005 per token
  • Supported Parameters: tools, response_format

​
Example Request

curl https://api.incredible.one/v1/models

​
Example Response

{
  "data": [
    {
      "id": "small-2",
      "canonical_slug": "small-2",
      "hugging_face_id": "",
      "name": "Incredible small-2",
      "created": 1730908800,
      "description": "Incredible's small-2 model finishes complex work across all your tools—no supervision required.",
      "context_length": 200000,
      "architecture": {
        "modality": "text->text",
        "input_modalities": ["text"],
        "output_modalities": ["text"],
        "tokenizer": "Minimax",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.0008",
        "completion": "0.0045",
        "request": "0",
        "image": "0",
        "web_search": "0",
        "internal_reasoning": "0"
      },
      "top_provider": {
        "context_length": 200000,
        "max_completion_tokens": null,
        "is_moderated": false
      },
      "per_request_limits": null,
      "supported_parameters": [
        "tools",
        "response_format"
      ],
      "default_parameters": {
        "temperature": null,
        "top_p": null,
        "frequency_penalty": null
      }
    },
    {
      "id": "small-1",
      "canonical_slug": "small-1",
      "hugging_face_id": "",
      "name": "Incredible small-1",
      "created": 1730908800,
      "description": "Incredible's small-1 model is aimed for accurately handling complex tool-chaining with large context.",
      "context_length": 200000,
      "architecture": {
        "modality": "text->text",
        "input_modalities": ["text"],
        "output_modalities": ["text"],
        "tokenizer": "GLM",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.001",
        "completion": "0.005",
        "request": "0",
        "image": "0",
        "web_search": "0",
        "internal_reasoning": "0"
      },
      "top_provider": {
        "context_length": 200000,
        "max_completion_tokens": null,
        "is_moderated": false
      },
      "per_request_limits": null,
      "supported_parameters": [
        "tools",
        "response_format"
      ],
      "default_parameters": {
        "temperature": null,
        "top_p": null,
        "frequency_penalty": null
      }
    }
  ]
}

​
Use Cases

  • Model Discovery: Query available models before making chat completion requests
  • Dynamic Model Selection: Build UIs that allow users to choose from available models
  • Pricing Information: Display pricing details to help users make informed choices
  • Capability Checking: Verify which parameters a specific model supports

​
Field Descriptions

​
Model Fields

FieldTypeDescription
idstringUnique identifier for the model (use this in chat completion requests)
canonical_slugstringCanonical slug for the model
hugging_face_idstringHugging Face model identifier (if applicable)
namestringHuman-readable name of the model
creatednumberUnix timestamp of when the model metadata was generated
descriptionstringDetailed description of the model’s capabilities
context_lengthnumberMaximum context window size in tokens

​
Architecture Fields

FieldTypeDescription
modalitystringThe model’s input/output modality (e.g., “text->text”)
input_modalitiesarraySupported input types
output_modalitiesarraySupported output types
tokenizerstringThe tokenizer used by the model
instruct_typestring|nullInstruction format type (if applicable)

​
Pricing Fields

All pricing values are strings representing USD cost per unit.
FieldTypeDescription
promptstringCost per input token
completionstringCost per output token
requeststringCost per API request
imagestringCost per image processed
web_searchstringCost per web search operation
internal_reasoningstringCost per internal reasoning token

​
Supported Parameters

The supported_parameters array indicates which optional parameters can be used with this model in chat completion requests:
  • tools - Model supports function/tool calling
  • response_format - Model supports structured output formats
  • temperature - Model supports temperature parameter
  • top_p - Model supports top_p sampling
  • frequency_penalty - Model supports frequency penalty
  • presence_penalty - Model supports presence penalty
  • max_tokens - Model supports max_tokens limit
  • tool_choice - Model supports forced tool selection

​
Notes

  • The created timestamp is generated dynamically at request time
  • All pricing is subject to change; check this endpoint regularly for current rates
  • Models are added and updated regularly; query this endpoint to discover new capabilities
  • The schema follows the OpenRouter API standard for compatibility