Skip to main content

What Is TokenLab?

TokenLab is an AI API aggregation platform that gives you unified access to hundreds of AI models from providers such as OpenAI, Anthropic, Google, DeepSeek, Moonshot, MiniMax, and more.

Native + Compatible

Use native Anthropic/Gemini routes when provider behavior matters, or OpenAI-compatible /v1 routes for existing OpenAI-style tools.

Native Formats

Call OpenAI, Anthropic, Gemini, and Responses-style endpoints from one platform.

Pay As You Go

No subscriptions. Only pay for what you actually use.

High Availability

Smart routing, failover, and multi-channel support improve reliability.

Supported Capabilities

The public catalog changes over time. Use /v1/models, recommended_for, or the Models page for exact current availability; the examples below use current public model IDs.
CapabilityDescriptionExample models
Chat & ReasoningText generation, planning, toolsgpt-5.4, claude-sonnet-4-6, deepseek-r1
Vision & MultimodalImage understanding and multimodal chatgpt-4o, claude-sonnet-4-6, gemini-3.5-flash
Image Generation & EditingText-to-image and image editinggpt-image-2, flux-pro, qwen-image-plus
Video GenerationText-to-video, image-to-video, reference video, and motion controlveo3.1, wan-2.7, kling-3.0-video, happyhorse-1.0
Audio & Realtime WebSocketTTS, transcription, audio translation, and realtime WebSocket sessionsgpt-4o-mini-tts, whisper-1, gpt-realtime
Embeddings & RerankText vectorization and rerankingtext-embedding-3-small, qwen3-vl-rerank
TranslationText translation and WebSocket speech translation workflowsdoubao-seed-translation, gpt-realtime-translate
Music & 3DMusic and 3D asset generationsuno-music, tripo-h3.1
WorldsWorld generation, status polling, and media asset workflowsUse /v1/worlds/generations and the Models API for current availability

Choose the Request Format

Start with the route that matches the behavior you need. Use native Anthropic/Gemini routes for provider-native features; use OpenAI-compatible /v1/chat/completions when migrating existing OpenAI-style chat code.
curl https://api.tokenlab.sh/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "Explain what TokenLab does in one sentence."}
    ]
  }'
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.tokenlab.sh/v1"
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Explain what TokenLab does in one sentence."}]
)

print(response.choices[0].message.content)
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-api-key',
  baseURL: 'https://api.tokenlab.sh/v1'
});

const response = await client.chat.completions.create({
  model: 'gpt-5.4',
  messages: [{ role: 'user', content: 'Explain what TokenLab does in one sentence.' }],
});

console.log(response.choices[0].message.content);
Use POST /v1/responses only when you explicitly need Responses-specific behavior. It is not the default compatibility path across all models.

Key Features

Multiple API Formats

Use OpenAI, Anthropic, Gemini, or Responses-native formats with one account.

Agent-First Errors

Structured hints help coding agents self-correct faster.

Integration Coverage

Connect IDEs, SDKs, frameworks, and chat apps with fewer provider-specific changes.

Next Steps

Quickstart

Get your first request working in a couple of minutes.

API Reference

Explore the endpoint-by-endpoint reference.

Integrations

Start with SDK, IDE, and app integrations.

Models

Browse current model availability and pricing.