cURL

cURL is the fastest way to try the API without installing an SDK.

Chat Completions

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Streaming

curl -N https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "Count to 5"}],
    "stream": true
  }'

-N disables buffering so SSE chunks print as they arrive.

File upload

curl https://llmtr.com/v1/files \
  -H "Authorization: Bearer sk_your_key" \
  -F "provider=google" \
  -F "purpose=user_upload" \
  -F "file=@./document.pdf"

Environment variable

Don’t inline the key — use an env var:

export LLMTR_API_KEY="sk_your_key"

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMTR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4o","messages":[{"role":"user","content":"Hi"}]}'

Formatted response

Use jq to pretty-print:

curl ... | jq '.choices[0].message.content'