Access GPT-4o, Claude, Gemini and 50+ models through a single API. Up to 70% cheaper than direct pricing. Pay as you go.
One API key, every model. Compatible with OpenAI SDK. No code changes required.
Aggregated pricing across providers. Same models, fraction of the cost. No minimum spend required.
Drop-in replacement for OpenAI API. Change the base URL and you're done. Works with every SDK.
Automatic routing across providers. If one goes down, traffic seamlessly switches to another.
SSE streaming for all models. Real-time token delivery with zero buffering and low latency.
Track every request, token, and dollar. Per-model breakdowns and real-time dashboard.
No subscriptions. No minimums. Top up with WeChat, Alipay, or USDT and use what you need.
Compare with direct provider pricing. All prices per 1M tokens (USD).
| Model | Our Input | Direct Input | Our Output | Direct Output | Savings |
|---|---|---|---|---|---|
| GPT-4o HOT | $1.50 | $2.50 | $6.00 | $10.00 | -40% |
| GPT-4o Mini | $0.09 | $0.15 | $0.36 | $0.60 | -40% |
| Claude 3.5 Sonnet | $1.80 | $3.00 | $9.00 | $15.00 | -40% |
| Claude 3 Opus | $9.00 | $15.00 | $45.00 | $75.00 | -40% |
| Gemini 1.5 Pro NEW | $1.75 | $3.50 | $7.00 | $10.50 | -50% |
| DeepSeek V3 | $0.07 | $0.27 | $0.14 | $1.10 | -70% |
| Llama 3.1 405B | $1.80 | $3.00 | $1.80 | $3.00 | -40% |
All major models accessible through a single OpenAI-compatible endpoint.
Create an account in seconds. No credit card required to explore.
Sign in or create an account to continue
Loading...
Use your API key with any OpenAI-compatible SDK. Simply change the base URL to our endpoint.
from openai import OpenAI client = OpenAI( api_key="tp-your-api-key", base_url="https://your-domain.com/v1" ) response = client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "Hello!"}] ) print(response.choices[0].message.content)
curl https://your-domain.com/v1/chat/completions \ -H "Authorization: Bearer tp-your-api-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4o", "messages": [{"role": "user", "content": "Hello!"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: "tp-your-api-key", baseURL: "https://your-domain.com/v1", }); const response = await client.chat.completions.create({ model: "gpt-4o", messages: [{ role: "user", content: "Hello!" }], }); console.log(response.choices[0].message.content);
Loading...
Loading...
Loading...