Claude Code
Route Claude Code at LLMRPM's Anthropic-compatible endpoint.
Configuration
| Setting | Value |
|---|---|
| API shape | Anthropic-compatible |
| Base URL | https://llmrpm.com/api |
| Auth | Authorization: Bearer llmrpm_... |
- Set
ANTHROPIC_AUTH_TOKENto your LLMRPM API key so the client sends a bearer token. - Set
ANTHROPIC_BASE_URLtohttps://llmrpm.com/api— the client appends/v1/messages. - Set default model IDs with
ANTHROPIC_DEFAULT_SONNET_MODELandANTHROPIC_DEFAULT_HAIKU_MODEL. - Increase
API_TIMEOUT_MSfor long, tool-heavy sessions.
Example
settings.json
{
"env": {
"ANTHROPIC_AUTH_TOKEN": "llmrpm_YOUR_KEY",
"ANTHROPIC_BASE_URL": "https://llmrpm.com/api",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-sonnet-5",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-haiku-4.5",
"API_TIMEOUT_MS": "3000000"
}
}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
| Symptom | Cause & fix |
|---|---|
| Authentication error | Check that the API key has no extra spaces and has not been revoked in the dashboard. |
| Model rejected | Use a public model ID returned by GET /api/v1/models; do not use display names or aliases. |
| Connection issue | Confirm the configured base URL is exactly the one shown above and that your network allows HTTPS to llmrpm.com. |
Notes
- Claude Code calls /v1/messages, not /v1/chat/completions.
- LLMRPM authenticates with a bearer token, so use ANTHROPIC_AUTH_TOKEN rather than an x-api-key value.
- If authentication fails, confirm the key has not been revoked in the dashboard.