AI Gateway

The Curate-Me AI Gateway is the control plane between your application and LLM providers. You keep your existing SDK, swap the base URL, add a Curate-Me key, and every request gets governance, routing, cost tracking, and auditability before it reaches the model.

What changes in your app


# Before
OPENAI_BASE_URL=https://api.openai.com/v1
 
# After
OPENAI_BASE_URL=https://api.curate-me.ai/v1/openai
X-CM-API-Key: cm_sk_xxx

You still send normal provider payloads. The gateway preserves standard JSON responses and streaming SSE behavior.

What the gateway adds

Layer	What it does
Governance	Applies rate limits, budget controls, model access checks, PII scanning, content safety, and HITL approval gates
Routing	Resolves model aliases, matches the correct provider, and supports provider-scoped base URLs
Observability	Adds request IDs, spend headers, retry metadata, usage logs, and health visibility
Resilience	Retries transient upstream failures, exposes idempotency keys, and protects against provider outages
Operations	Supports stored provider secrets, admin APIs, usage dashboards, approval queues, and runner-aware cost controls

Endpoint patterns

Pattern	Example	Best for
Provider-namespaced base URL	`https://api.curate-me.ai/v1/openai`	OpenAI-compatible SDKs
Anthropic base URL	`https://api.curate-me.ai/v1/anthropic`	Anthropic SDKs
Generic OpenAI-compatible endpoint	`POST /v1/chat/completions`	Direct HTTP or custom clients
Generic Anthropic endpoint	`POST /v1/messages`	Direct HTTP or Anthropic-style payloads
Model discovery	`GET /v1/models`	Listing routable models through the gateway

Supported providers

51 providers across 7 tiers:

Provider tier	Built-in providers
Core (Tier 1)	OpenAI, Anthropic, Google, DeepSeek, Perplexity
OpenClaw favorites (Tier 2)	Moonshot, MiniMax, ZAI, Cerebras, Qwen
Developer staples (Tier 3)	Groq, Mistral, xAI, Together, Fireworks, Cohere, OpenRouter
Extended (Tiers 4-7)	AI21, Azure OpenAI, AWS Bedrock, Hugging Face, Replicate, Ollama, and 28 more

See the full list on the Providers & Routing page.

Authentication

Every proxy request needs:

Credential	Purpose
`X-CM-API-Key`	Authenticates your request to Curate-Me
`X-Provider-Key` or `Authorization: Bearer <provider-key>`	Authenticates the upstream call to the model provider

You can also store provider credentials through the admin APIs or dashboard provider secrets flow and stop sending X-Provider-Key on each request.

Common response headers

Header	Meaning
`X-CM-Request-ID`	Gateway request ID for tracing, support, and log lookup
`X-CM-Cost`	Estimated request cost in USD
`X-CM-Daily-Cost`	Current daily spend for the org
`X-CM-Daily-Budget`	Active daily budget used for governance decisions
`X-RateLimit-Limit`	Requests allowed in the current rate-limit window
`X-RateLimit-Remaining`	Requests left in the window
`X-RateLimit-Reset`	Unix timestamp when the window resets
`X-Idempotency-Key`	Stable key used for retry-safe upstream execution
`X-Process-Time`	Gateway processing time in seconds

Quick examples

OpenAI SDK


from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.curate-me.ai/v1/openai",
    api_key="sk-your-openai-key",
    default_headers={"X-CM-API-Key": "cm_sk_xxx"},
)
 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
)

Anthropic SDK


import anthropic
 
client = anthropic.Anthropic(
    base_url="https://api.curate-me.ai/v1/anthropic",
    api_key="sk-ant-your-key",
    default_headers={"X-CM-API-Key": "cm_sk_xxx"},
)
 
message = client.messages.create(
    model="claude-sonnet-4-5-20250929",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)

cURL


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: $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Local development


cd services/backend
poetry install
poetry run uvicorn src.main_gateway:app --reload --port 8002

Then point your SDK at http://localhost:8002/v1/openai, http://localhost:8002/v1/anthropic, or another provider path.