$ welcome to
noxery
OpenAI-compatible inference API. Multiple models, one endpoint.
Models
A selection of available models. See the Models page for the full list.
GPT-5.6 Sol
gpt-5.6-sol
flagship
free 1M/day · 1B/mo
Most capable, highest quality.
openai/gpt-oss-20b
openai/gpt-oss-20b
balanced
ctx 128k · out 64k
free 100k/day · 2M/mo
Balanced speed and quality.
openai/gpt-oss-120b
openai/gpt-oss-120b
flagship
ctx 128k · out 64k
free 100k/day · 2M/mo
Most capable, highest quality.
qwen/qwen3.6-27b
qwen/qwen3.6-27b
vision
vision
ctx 128k · out 16k
free 100k/day · 2M/mo
Text and image understanding.
qwen/qwen3.8-27b
qwen/qwen3.8-27b
vision
vision
ctx 128k · out 16k
free 100k/day · 2M/mo
Text and image understanding.
qwen-max
qwen-max
flagship
free 100k/day · 2M/mo
Most capable, highest quality.
Quick Start
Endpoint, authentication, and a minimal request.
base url: https://noxery.tr/v1 · auth: Bearer nox-YOUR_KEY
curl https://noxery.tr/v1/chat/completions \
-H "Authorization: Bearer nox-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-sol",
"messages": [{"role": "user", "content": "hi"}]
}'
-H "Authorization: Bearer nox-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-sol",
"messages": [{"role": "user", "content": "hi"}]
}'
Features
What this API provides.
- OpenAI-compatible API
- Streaming responses (SSE)
- API key management
- Usage & token tracking
- Per-model quota limits
- Text and vision models
FAQ
Common questions.
How do I get an API key?
Create an account, then generate a key from the API Keys page. Keys are shown only once.
Which models are available?
See the Models page, or call GET /v1/models with your key.
Is it compatible with the OpenAI SDK?
Yes. Point the base URL at https://noxery.tr/v1 and pass your nox- key.
How is usage tracked?
Tokens and requests are logged per key and shown on the Usage page.
How do I call the endpoint?
POST /v1/chat/completions with a Bearer token and a JSON body containing model and messages.