Models

Overview

The Models API lets you discover all 100+ models available through AllRoutes, including pricing, capabilities, and provider information.

List All Models

GET https://api.allroutes.ai/v1/models

Returns all models available on the gateway.

Query Parameters

Parameter	Type	Description
provider	string	Filter by provider name (e.g., openai, anthropic, google)
category	string	Filter by category (e.g., chat, embedding, image, code)
capability	string	Filter by capability (e.g., streaming, function_calling, vision, json_mode)
active	boolean	Filter by active status (default: true)

Example

curl https://api.allroutes.ai/v1/models?provider=openai \
  -H "Authorization: Bearer allroutes_sk_..."

Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "name": "GPT-4o",
      "provider": "openai",
      "context_length": 128000,
      "input_cost_per_token": 0.0000025,
      "output_cost_per_token": 0.00001,
      "is_active": true,
      "capabilities": ["streaming", "function_calling", "vision", "json_mode"],
      "category": "chat",
      "created": 1714000000
    }
  ]
}

Model Fields

Field	Type	Description
id	string	Model identifier used in API requests
name	string	Human-readable display name
provider	string	Provider name
context_length	integer	Maximum context window in tokens
input_cost_per_token	float	Cost per input token in USD
output_cost_per_token	float	Cost per output token in USD
is_active	boolean	Whether the model is currently available
capabilities	array	Supported features
category	string	Model category

Get Model Details

GET https://api.allroutes.ai/v1/models/:id

Returns detailed information for a specific model.

curl https://api.allroutes.ai/v1/models/gpt-4o \
  -H "Authorization: Bearer allroutes_sk_..."

Response

{
  "id": "gpt-4o",
  "object": "model",
  "name": "GPT-4o",
  "provider": "openai",
  "context_length": 128000,
  "input_cost_per_token": 0.0000025,
  "output_cost_per_token": 0.00001,
  "is_active": true,
  "capabilities": ["streaming", "function_calling", "vision", "json_mode"],
  "category": "chat",
  "max_output_tokens": 16384,
  "supports_streaming": true,
  "supports_function_calling": true,
  "supports_vision": true,
  "supports_json_mode": true,
  "created": 1714000000
}

Search Models

GET https://api.allroutes.ai/v1/models/search

Full-text search across model names, descriptions, and providers.

Parameter	Type	Description
q	string	Search query (e.g., "fast coding", "vision")
provider	string	Narrow results to a specific provider
limit	integer	Max results (default: 20, max: 100)

curl "https://api.allroutes.ai/v1/models/search?q=vision&provider=openai" \
  -H "Authorization: Bearer allroutes_sk_..."

Compare Models

GET https://api.allroutes.ai/v1/models/compare

Compare pricing, capabilities, and context lengths for multiple models side by side.

Parameter	Type	Description
models	string	Comma-separated model IDs to compare

curl "https://api.allroutes.ai/v1/models/compare?models=gpt-4o,claude-sonnet-4-20250514,gemini-2.0-flash" \
  -H "Authorization: Bearer allroutes_sk_..."

Response

{
  "models": [
    {
      "id": "gpt-4o",
      "provider": "openai",
      "context_length": 128000,
      "input_cost_per_token": 0.0000025,
      "output_cost_per_token": 0.00001,
      "capabilities": ["streaming", "function_calling", "vision", "json_mode"]
    },
    {
      "id": "claude-sonnet-4-20250514",
      "provider": "anthropic",
      "context_length": 200000,
      "input_cost_per_token": 0.000003,
      "output_cost_per_token": 0.000015,
      "capabilities": ["streaming", "function_calling", "vision", "json_mode"]
    },
    {
      "id": "gemini-2.0-flash",
      "provider": "google",
      "context_length": 1048576,
      "input_cost_per_token": 0.00000015,
      "output_cost_per_token": 0.0000006,
      "capabilities": ["streaming", "function_calling", "vision", "json_mode"]
    }
  ]
}

SDK Examples

Python

models = client.list_models()
for model in models:
    print(f"{model['id']} by {model['provider']}")

Node.js

const models = await client.listAllRoutesModels();
for (const model of models) {
  console.log(`${model.name} by ${model.provider} - ctx: ${model.context_length}`);
}

Go

models, err := client.ListModels(ctx)
if err != nil {
    log.Fatal(err)
}
for _, m := range models {
    fmt.Printf("%s (%s) by %s -- ctx: %d\n",
        m.DisplayName, m.ID, m.ProviderName, m.ContextWindow)
}

See Also

• Chat Completions -- send completions to any listed model
• Embeddings -- list embedding models specifically
• Model Groups -- alias multiple models behind one identifier
• Free Tier -- which models are available at no cost
• BYOK -- restrict the catalog to your own provider keys