cURL / HTTP

Configuration

• Export LLMRPM_API_KEY in your shell before sending requests.
• Send Authorization: Bearer $LLMRPM_API_KEY on every request — both wire formats use bearer auth.
• Use /api/v1/chat/completions for the OpenAI format and /api/v1/messages for the Anthropic format.
• Add Content-Type: application/json on every POST request.

Example

export LLMRPM_API_KEY="llmrpm_YOUR_KEY"
export LLMRPM_BASE_URL="https://llmrpm.com/api/v1"

curl https://llmrpm.com/api/v1/chat/completions \
  -H "Authorization: Bearer $LLMRPM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [
      { "role": "system", "content": "You are a concise release assistant." },
      { "role": "user", "content": "Write three product taglines." }
    ],
    "stream": false,
    "max_tokens": 400
  }'

curl https://llmrpm.com/api/v1/messages \
  -H "Authorization: Bearer $LLMRPM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 400,
    "messages": [
      { "role": "user", "content": "Draft a deployment checklist." }
    ]
  }'

Recommended models

Any public ID from the model list works. Common picks:

• claude-sonnet-5— strong model for reasoning, refactors, and coding agents.
• claude-haiku-4.5— fast option for autocomplete, small questions, and lightweight tasks.
• deepseek-v4-pro— alternative based on your active catalog and plan.

Troubleshooting

Notes

• Both endpoints live under the same /api/v1 path and share one key.
• For streaming, set "stream": true and read the server-sent event lines.