Skip to main content

​
1. Get an API key

Email hello@tera.gw to request a key. Keys are formatted as sk-tera-....

​
2. Send your first request

curl https://api.tera.gw/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TERA_API_KEY" \
  -d '{
    "model": "Qwen/Qwen2.5-7B-Instruct",
    "messages": [
      {"role": "user", "content": "Say hello in one short sentence."}
    ],
    "max_tokens": 64
  }'

​
3. Stream the response

Add "stream": true to get token-by-token output over Server-Sent Events. See Streaming for the full event format. 
curl https://api.tera.gw/v1/chat/completions \
  -H "Authorization: Bearer $TERA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-7B-Instruct",
    "messages": [{"role": "user", "content": "Count to five."}],
    "stream": true
  }'

​
What next?

Browse models

Pick the right model for your workload.

OpenAI compatibility

Migrating from OpenAI? Read this first.

Reasoning models

How to use chain-of-thought reasoning with Qwen3.5.

Tool calling

Function calling with OpenAI-compatible schemas.