OpenAI 兼容接口 / GPT-4o, Llama 3.3, DeepSeek R1, Grok-3 / 低价高质
Drop-in replacement for OpenAI API. Just change the base URL and API key.
https://ai66-relay.YOUR_SUBDOMAIN.workers.dev/v1
curl https://ai66-relay.YOUR_SUBDOMAIN.workers.dev/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-ai66-YOUR_KEY" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello!"}]
}'
from openai import OpenAI
client = OpenAI(
base_url="https://ai66-relay.YOUR_SUBDOMAIN.workers.dev/v1",
api_key="sk-ai66-YOUR_KEY"
)
resp = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
print(resp.choices[0].message.content)
const resp = await fetch(
"https://ai66-relay.YOUR_SUBDOMAIN.workers.dev/v1/chat/completions",
{
method: "POST",
headers: {
"Content-Type": "application/json",
"Authorization": "Bearer sk-ai66-YOUR_KEY"
},
body: JSON.stringify({
model: "llama-3.3-70b",
messages: [{ role: "user", content: "Hello!" }]
})
}
);
const data = await resp.json();
console.log(data.choices[0].message.content);
curl https://ai66-relay.YOUR_SUBDOMAIN.workers.dev/v1/models
POST /v1/chat/completions | Chat (OpenAI compatible) |
POST /v1/completions | Text completion |
GET /v1/models | List models |
POST /v1/embeddings | Embeddings (coming soon) |
60 requests per minute per API key.
All prices in USD per million tokens. Input and output priced equally.
| Model | Input $/M | Output $/M | Providers |
|---|---|---|---|
| gpt-4o | $2.00 | $2.00 | GitHub Models |
| gpt-4o-mini | $0.50 | $0.50 | GitHub Models |
| llama-3.3-70b | $0.30 | $0.30 | Groq / SambaNova / NVIDIA |
| deepseek-r1 | $1.00 | $1.00 | GitHub Models |
| grok-3 | $3.00 | $3.00 | GitHub Models |
| mistral-small | $0.20 | $0.20 | Mistral AI |
Minimum top-up: $5 USD
Send USDT on BSC network only. Contact support with your tx hash.