LLM as a Service
Use Llama, Qwen and other powerful open models through a single OpenAI-compatible API. No monthly fee; you pay from your balance only for the tokens you use.
curl https://api.haizora.com/v1/ai/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"messages": [
{ "role": "user", "content": "Merhaba!" }
],
"stream": true
}'Models and pricing
The list and prices are live. Prices are USD per 1 million tokens.
Loading models…
Get started in three steps
Sign up and top up
Create a free account and add any amount to your balance from the dashboard.
Create an API key
Get your key from the AI API section of the dashboard; it is shown only once.
Send your first request
Change base_url in your OpenAI client and pick a model from the list.
Why Haizora LLM API?
OpenAI-compatible
Change only base_url and the key in your existing code. Chat, streaming, embedding and rerank endpoints are ready.
Pay as you go
No monthly fee or commitment. Each request is charged to your balance by its token count.
Spending control
A monthly spend limit and low-balance alerts mean no surprise bills.
Ready for RAG
Build search and document-grounded assistants with embedding and rerank models.
Per-key tracking
Multiple API keys; usage and spend broken down by model in your dashboard.
Up-to-date catalog
The model list is refreshed daily; new models are available with no extra work.
How is your data processed?
Your requests are forwarded to and processed by our infrastructure provider abroad (USA) that runs the models. We do not store request or response content; only the model name, token count and time are recorded for billing. Requests containing personal data constitute a cross-border transfer; as the data controller, you are responsible for providing the required notices and obtaining consent.
Send your first request today
Create an account, top up your balance and start using the OpenAI-compatible API in minutes.