Models API

List available models and retrieve model information.

List Models

Get a list of all available models in your workspace.

Endpoint

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

Authentication

Authorization: Bearer YOUR_API_KEY

Request

cURLPythonNode.js

bash

curl https://api.tokenlio.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.tokenlio.ai/v1"
)

models = client.models.list()

for model in models.data:
    print(f"{model.id}: {model.owned_by}")

javascript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.tokenlio.ai/v1',
});

const models = await client.models.list();

for (const model of models.data) {
  console.log(`${model.id}: ${model.owned_by}`);
}

Response

json

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4-turbo",
      "object": "model",
      "created": 1699999999,
      "owned_by": "openai"
    },
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1699999999,
      "owned_by": "openai"
    },
    {
      "id": "claude-3-5-sonnet",
      "object": "model",
      "created": 1699999999,
      "owned_by": "anthropic"
    }
  ]
}

Retrieve Model

Get detailed information about a specific model.

Endpoint

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

Request

cURLPythonNode.js

bash

curl https://api.tokenlio.ai/v1/models/gpt-4-turbo \
  -H "Authorization: Bearer YOUR_API_KEY"

python

model = client.models.retrieve("gpt-4-turbo")
print(f"Model: {model.id}")
print(f"Owner: {model.owned_by}")

javascript

const model = await client.models.retrieve('gpt-4-turbo');
console.log(`Model: ${model.id}`);
console.log(`Owner: ${model.owned_by}`);

Response

json

{
  "id": "gpt-4-turbo",
  "object": "model",
  "created": 1699999999,
  "owned_by": "openai"
}

Public Models Endpoint

Get public pricing information without authentication.

Endpoint

GET https://api.tokenlio.ai/api/v1/public/models

No Authentication Required

This endpoint is publicly accessible for pricing information.

Request

bash

curl https://api.tokenlio.ai/api/v1/public/models

Response

json

[
  {
    "model_id": "gpt-4-turbo",
    "display_name": "GPT-4 Turbo",
    "provider": "openai",
    "category": "chat",
    "our_price": {
      "input": 0.008,
      "output": 0.024,
      "unit": "per 1M tokens"
    },
    "official_price": {
      "input": 0.01,
      "output": 0.03,
      "source": "openai"
    },
    "savings_percent": 20,
    "capabilities": ["streaming", "function_calling"],
    "context_length": 128000
  }
]

Response Fields

Field	Type	Description
`model_id`	string	Model identifier for API calls
`display_name`	string	Human-readable model name
`provider`	string	Model provider (openai, anthropic, etc.)
`category`	string	Model category (chat, embedding, image, etc.)
`our_price`	object	Sub2API pricing
`official_price`	object	Official provider pricing (if available)
`savings_percent`	number	Percentage saved vs official price
`capabilities`	array	Supported features
`context_length`	integer	Maximum context window in tokens

Model Categories

Models are categorized by their primary function:

Chat Models

Conversational AI for text generation:

GPT-4, GPT-3.5
Claude 3.5, Claude 3
Gemini 1.5, Gemini 1.0

Embedding Models

Convert text to vector representations:

text-embedding-3-small
text-embedding-3-large
text-embedding-ada-002

Image Models

Generate or analyze images:

DALL-E 3
DALL-E 2

Audio Models

Speech-to-text and text-to-speech:

Whisper
TTS models

Model Properties

Context Length

Maximum tokens the model can process:

Model	Context Length
GPT-4 Turbo	128,000
GPT-4	8,192
Claude 3.5 Sonnet	200,000
Gemini 1.5 Pro	1,000,000

Capabilities

Common capabilities:

streaming: Supports token streaming
function_calling: Can call functions/tools
json_mode: Structured JSON output
vision: Can process images

Usage Examples

Filter by Provider

python

models = client.models.list()

openai_models = [m for m in models.data if m.owned_by == "openai"]
anthropic_models = [m for m in models.data if m.owned_by == "anthropic"]

print(f"OpenAI models: {len(openai_models)}")
print(f"Anthropic models: {len(anthropic_models)}")

Check Model Availability

python

def is_model_available(model_id: str) -> bool:
    try:
        client.models.retrieve(model_id)
        return True
    except Exception:
        return False

if is_model_available("gpt-4-turbo"):
    print("GPT-4 Turbo is available")

Get Pricing Information

python

import requests

response = requests.get("https://api.tokenlio.ai/api/v1/public/models")
models = response.json()

for model in models:
    if model.get("savings_percent"):
        print(f"{model['display_name']}: Save {model['savings_percent']}%")

Model Identifiers

Use these identifiers in API requests:

OpenAI

gpt-4-turbo
gpt-4
gpt-3.5-turbo
gpt-3.5-turbo-16k

Anthropic

claude-3-5-sonnet
claude-3-opus
claude-3-sonnet
claude-3-haiku

Google

gemini-1.5-pro
gemini-1.5-flash
gemini-1.0-pro

See the Models & Pricing page for the complete list with pricing.

Error Handling

Model Not Found

json

{
  "error": {
    "message": "Model 'invalid-model' not found",
    "type": "invalid_request_error",
    "code": "model_not_found"
  }
}

No Access

json

{
  "error": {
    "message": "You do not have access to this model",
    "type": "permission_error",
    "code": "model_not_accessible"
  }
}

Best Practices

Cache Model Lists

Don't fetch the model list on every request:

python

from functools import lru_cache
from datetime import datetime, timedelta

@lru_cache(maxsize=1)
def get_cached_models():
    return client.models.list()

# Refresh cache periodically
models = get_cached_models()

Validate Model Selection

Check model availability before making requests:

python

def validate_model(model_id: str) -> bool:
    models = client.models.list()
    available = [m.id for m in models.data]
    return model_id in available

if not validate_model("gpt-4-turbo"):
    raise ValueError("Model not available")

Handle Model Changes

Models may be deprecated or renamed:

python

MODEL_ALIASES = {
    "gpt-4-0613": "gpt-4",
    "gpt-3.5-turbo-0613": "gpt-3.5-turbo",
}

def resolve_model(model_id: str) -> str:
    return MODEL_ALIASES.get(model_id, model_id)

Models API ​

List Models ​

Endpoint ​

Authentication ​

Request ​

Response ​

Retrieve Model ​

Endpoint ​

Request ​

Response ​

Public Models Endpoint ​

Endpoint ​

No Authentication Required ​

Request ​

Response ​

Response Fields ​

Model Categories ​

Chat Models ​

Embedding Models ​

Image Models ​

Audio Models ​

Model Properties ​

Context Length ​

Capabilities ​

Usage Examples ​

Filter by Provider ​

Check Model Availability ​

Get Pricing Information ​

Model Identifiers ​

OpenAI ​

Anthropic ​

Google ​

Error Handling ​

Model Not Found ​

No Access ​

Best Practices ​

Cache Model Lists ​

Validate Model Selection ​

Handle Model Changes ​

Next Steps ​

Need Help? ​

Models API

List Models

Endpoint

Authentication

Request

Response

Retrieve Model

Endpoint

Request

Response

Public Models Endpoint

Endpoint

No Authentication Required

Request

Response

Response Fields

Model Categories

Chat Models

Embedding Models

Image Models

Audio Models

Model Properties

Context Length

Capabilities

Usage Examples

Filter by Provider

Check Model Availability

Get Pricing Information

Model Identifiers

OpenAI

Anthropic

Google

Error Handling

Model Not Found

No Access

Best Practices

Cache Model Lists

Validate Model Selection

Handle Model Changes

Next Steps

Need Help?