Skip to main content
GET
/
v1
/
models
/
{model_id}
Typescript
const client = new Dedalus();

const result = await client.models.retrieve(modelID);
{
  "id": "<string>",
  "provider": "openai",
  "created_at": "2023-11-07T05:31:56Z",
  "display_name": "<string>",
  "description": "<string>",
  "version": "<string>",
  "capabilities": {
    "text": true,
    "vision": true,
    "image_generation": true,
    "audio": true,
    "tools": true,
    "structured_output": true,
    "streaming": true,
    "thinking": true,
    "input_token_limit": 123,
    "output_token_limit": 123
  },
  "defaults": {
    "temperature": 123,
    "top_p": 123,
    "top_k": 123,
    "max_output_tokens": 123
  },
  "provider_info": {
    "routing": [
      {
        "endpoint": "/v1/chat/completions",
        "upstream_api": "openai/chat/completions"
      }
    ],
    "status": "enabled"
  },
  "provider_declared_generation_methods": [
    "<string>"
  ]
}

Documentation Index

Fetch the complete documentation index at: https://docs.dedaluslabs.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Retrieve detailed information about a specific model, including capabilities, pricing, token limits, and routing. The model_id uses the provider/model format (e.g., openai/gpt-4o, anthropic/claude-opus-4-5).

​
Usage Examples

curl https://api.dedaluslabs.ai/v1/models/openai/gpt-4o \
  -H "x-api-key: $DEDALUS_API_KEY"

​
Example Response

{
  "id": "openai/gpt-4o",
  "provider": "openai",
  "created_at": "2024-05-13T00:00:00Z",
  "display_name": "GPT-4o",
  "description": "Fast, multimodal flagship model.",
  "capabilities": {
    "text": true,
    "vision": true,
    "tools": true,
    "structured_output": true,
    "streaming": true
  },
  "token_limits": {
    "input": 128000,
    "output": 16384
  },
  "pricing": {
    "input_per_million": 2.5,
    "output_per_million": 10.0,
    "cached_input_per_million": 1.25
  },
  "provider_info": {
    "routing": [
      {
        "endpoint": "/v1/chat/completions",
        "upstream_api": "openai/chat/completions"
      }
    ],
    "status": "enabled"
  }
}

Authorizations

​
Authorization
string
header
required

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

Path Parameters

​
model_id
string
required

Response

Successful Response

Unified model metadata across all providers.

Combines provider-specific schemas into a single, consistent format. Fields that aren't available from a provider are set to None.

​
id
string
required

Unique model identifier with provider prefix (e.g., 'openai/gpt-4')

​
provider
enum<string>
required

Provider that hosts this model

Available options:
openai,
anthropic,
google,
xai,
deepseek,
mistral,
groq,
fireworks,
cohere,
together,
cerebras,
perplexity,
moonshot
​
created_at
string<date-time>
required

When the model was released (RFC 3339)

​
display_name
string | null

Human-readable model name

​
description
string | null

Model description

​
version
string | null

Model version identifier

​
capabilities
ModelCapabilities · object

Normalized model capabilities

​
defaults
ModelDefaults · object

Provider-declared default parameters

​
provider_info
ModelProviderInfo · object

Typed provider-specific metadata

​
provider_declared_generation_methods
string[] | null

Provider-specific generation method names (None = not declared)

Last modified on May 2, 2026