cURL Quickstart

No SDK required. The gateway is a standard HTTP proxy.

Health Check (No Auth)


curl https://api.curate-me.ai/v1/health

Chat Completion (OpenRouter — 200+ models)

The simplest way to get started. OpenRouter gives you access to models from every major provider through a single path:


curl https://api.curate-me.ai/v1/openrouter/chat/completions \
  -H "X-CM-API-Key: cm_sk_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-haiku-4-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Chat Completion (Direct OpenAI)

If you have your own OpenAI key, pass it via X-Provider-Key:


curl https://api.curate-me.ai/v1/openai/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-CM-API-Key: cm_sk_xxx" \
  -H "X-Provider-Key: sk-your-openai-key" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Anthropic Messages (Direct)


curl https://api.curate-me.ai/v1/anthropic/messages \
  -H "Content-Type: application/json" \
  -H "X-CM-API-Key: cm_sk_xxx" \
  -H "X-Provider-Key: sk-ant-your-anthropic-key" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Streaming

Add "stream": true to the request body:


curl https://api.curate-me.ai/v1/openrouter/chat/completions \
  -H "X-CM-API-Key: cm_sk_xxx" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "anthropic/claude-haiku-4-5",
    "stream": true,
    "messages": [{"role": "user", "content": "Count to 10 slowly."}]
  }'

List Models


curl https://api.curate-me.ai/v1/models \
  -H "X-CM-API-Key: cm_sk_xxx"

Response Headers

Every gateway response includes:

Header	Description
`X-CM-Request-Id`	Unique request tracking ID inside the gateway
`X-CM-Cost`	Estimated cost of the request in USD
`X-CM-Governance-Time-Ms`	Milliseconds spent in the governance chain
`X-CM-Trace-Id`	W3C trace ID for distributed tracing
`X-CM-Daily-Cost`	Current daily spend for the org
`X-CM-Daily-Budget`	Active daily budget used by governance
`RateLimit-Limit`	Max requests per minute (IETF standard)
`RateLimit-Remaining`	Requests remaining in current window
`RateLimit-Reset`	Window reset timestamp

Error Codes

Code	Meaning
401	Invalid or missing gateway API key
403	Request blocked by governance policy, budget controls, or model access rules
202	Request is pending human approval
429	Rate limit exceeded
502	Upstream provider error