T
TokonLabv2
OpenAI-Compatible API · 3 models · 4-week MVP

One API for
All AI Models

Drop-in OpenAI replacement. Route to the cheapest, fastest, or best model — all through one unified endpoint. Sign up, get your key, start building in minutes.

Free tier available · No credit card required · Developer can be live in < 3 minutes

curl https://api.tokonlab.com/v1/chat/completions \
  -H "Authorization: Bearer sk-tokon-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cheap-model",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'
Base URL:api.tokonlab.com/v1
Auth:Bearer Token
Format:OpenAI Compatible
Markup:+3% platform fee

Three models. Every use case.

Abstract aliases route to the best underlying provider. No vendor lock-in.

💰Budget
cheap-model
Powered by DeepSeek

Maximum cost efficiency. Best for high-volume tasks, summarization, and simple Q&A where budget matters most.

128K
Context
~$0.14
Price
~800ms
Latency
High throughputCost optimizedLong context
⚡Speed
fast-model
Powered by OpenAI

Optimized for low latency. Ideal for real-time chat, interactive applications, and user-facing products.

64K
Context
~$0.50
Price
~200ms
Latency
Ultra-low latencyReal-time readyReliable
🧠Quality
best-model
Powered by Qwen

Maximum quality and reasoning. For complex analysis, code generation, and tasks requiring deep understanding.

128K
Context
~$0.22
Price
~1.2s
Latency
Best accuracyComplex reasoningMultilingual

Live in 3 minutes

From sign-up to first API call — no complex setup required.

01

Sign Up

Create a free account. No credit card required. Get 50 free requests per day.

Create account →
02

Generate API Key

Go to your dashboard and create an API key. Copy it — you'll use it in the next step.

Open dashboard →
03

Call the API

Replace your OpenAI base URL with ours. Change the model name. That's it.

Read quickstart →

How it works under the hood

Every request passes through auth, routing, and logging before reaching the provider.

Your App
Any OpenAI SDK
↓
API Gateway
POST /v1/chat/completions
↓
Auth Middleware
Validate Bearer token
↓
Router Engine
cheap → DeepSeek, fast → OpenAI, best → Qwen
↓
Provider Adapter
Request transform + response normalize
↓
Model Provider
DeepSeek / Qwen / OpenAI
↓
Logging + Billing
Record tokens, cost, latency → PostgreSQL

Simple, transparent pricing

Provider cost + 3% platform fee. No subscriptions, no hidden fees.

price = provider_cost × 1.03

3% platform fee covers routing, fallback, logging, and support. Both provider cost and your price are recorded for full transparency.

cheap-model
Provider cost$0.14/1M
Your price$0.144/1M
↓ vs $3.00 GPT-4o
fast-model
Provider cost$0.50/1M
Your price$0.515/1M
↓ vs $5.00 GPT-4
best-model
Provider cost$0.22/1M
Your price$0.227/1M
↓ vs $15.00 Claude 3.5