Access GPT-4o, DeepSeek, Grok, Llama, Qwen and more through a single OpenAI-compatible API. 4 models free forever.
One API key for all models. OpenAI SDK compatible. Plug and play.
4 models free forever. Qwen 2.5, Llama 3.1, Gemma 2, Phi-4 — no credit card needed.
Multi-backend routing with automatic failover. If one provider fails, we switch instantly.
GPT-4o, DeepSeek-R1, Grok-3, Llama 4, Qwen 72B and more. One key, all models.
Per-request cost in headers. Pay-as-you-go with USDT. No hidden fees, no surprises.
All pricing per million tokens. Free models have zero cost, unlimited use.
Standard OpenAI format. Works with any SDK instantly.
# Replace YOUR_API_KEY with your key curl https://ai66-relay.titangrid.workers.dev/v1/chat/completions \ -H "Authorization: Bearer sk-ai66-xxxxx" \ -H "Content-Type: application/json" \ -d '{ "model": "llama-3.1-8b", "messages": [{"role": "user", "content": "Hello!"}] }'
from openai import OpenAI client = OpenAI( api_key="sk-ai66-xxxxx", base_url="https://ai66-relay.titangrid.workers.dev/v1" ) # Free model - no charge! r = client.chat.completions.create( model="llama-3.1-8b", messages=[{"role": "user", "content": "Hello!"}] ) print(r.choices[0].message.content)
Sign up for a free API key. 4 free models + $1 credit included.
Get your API key instantly. 4 free models + $1 credit.
Manage keys, monitor usage, test models, recharge balance.
Base URL: https://ai66-relay.titangrid.workers.dev/v1
| Model | Requests | Input Tokens | Output Tokens | Cost |
|---|
| Model | In | Out | Cost | Time |
|---|
curl https://ai66-relay.titangrid.workers.dev/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.1-8b",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI client = OpenAI( api_key="YOUR_KEY", base_url="https://ai66-relay.titangrid.workers.dev/v1" ) r = client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "Hello!"}] ) print(r.choices[0].message.content)
import OpenAI from "openai"; const client = new OpenAI({ apiKey: "YOUR_KEY", baseURL: "https://ai66-relay.titangrid.workers.dev/v1" }); const r = await client.chat.completions.create({ model: "gpt-4o", messages: [{ role: "user", content: "Hello!" }] }); console.log(r.choices[0].message.content);
Send USDT to the address below. Balance updates within 5-30 minutes.