GPT models on /v1/chat/completions and /v1/responses. Keep the OpenAI SDK, change the base URL and the key.
gpt-6.1-sol−95%gpt-6-astra−95%gpt-6-sol−90%gpt-6-luna−50%Struck-through = the provider's official API price. Prices in USD, live from our billing.
10M input + 2M output tokens on GPT-6.1 Sol, no cache:
Our API speaks the OpenAI format: Chat Completions, the Responses API, streaming with usage, tool calling and reasoning parameters. Any library that lets you set base_url works without code changes.
Prices are live from our billing and shown next to OpenAI's published price. On a blended 3:1 input/output basis the saving is up to 95%.
The same key also runs Claude, Grok, DeepSeek, GLM and Kimi (31 models in total), so you can compare models or fall back between them without another account.
curl https://api.apixoai.online/v1/chat/completions \
-H "Authorization: Bearer sk-...your-key" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6.1-sol",
"messages":[{"role":"user","content":"Hello"}]}'That's about 111K tokens on Claude Fable 5. Valid 72h, for Google and Telegram sign-ups. Works on 13 models, including GPT-6.1 Sol, GPT-6 Luna, Claude Fable 5.
Sign up with Google, email or Telegram. Your API key is ready instantly ($0.10 free to test for Google and Telegram sign-ups).
Paste our base URL and your key into your SDK or tool. The docs have the exact config for each one.
Top up with crypto from $1. Every request shows its tokens and exact cost.
We buy model capacity in bulk and resell it per token. Same models, same API, a smaller margin.
The struck-through prices come from each provider's official page. Compare them yourself:
Start with the free credit or a $1 top-up. Your topped-up balance never expires and every request shows its exact cost.
More answers in the docs, or contact us.
Yes. Set base_url to our /v1 endpoint and use your key as api_key. Streaming, tools and JSON mode work as usual.
Yes, /v1/responses is supported alongside /v1/chat/completions.
Top up with crypto (USDT, USDC, BTC, ETH, LTC and more) from $1. No card and no subscription.
Yes. Cached input is billed at the model's cache price automatically.