Quickstart

Create a verified key and send the first request.

Create a verified key

Create an account, confirm its email address, and create an inference key in the console. Keys are shown once; store the value in your own secret manager.

Use the API base URL https://api.arnict.com/v1.
Use the available model ID qwen3.8-27b.
Keep the 30 requests-per-minute account limit in your retry policy.

Send a request

Arnict accepts the familiar OpenAI chat-completions shape. The response includes usage for non-streaming calls, and streaming calls request a final usage event.

bash

curl https://api.arnict.com/v1/chat/completions \
+  -H "Authorization: Bearer $ARNICT_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"qwen3.8-27b","messages":[{"role":"user","content":"Hello"}],"max_tokens":64}'

Authentication →

Reference model

qwen3.8-27b