Proxy Endpoints

POST /v1/chat/completions

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello, world!"}
  ],
  "stream": false,
  "temperature": 0.7,
  "max_tokens": 256
}

HTTP/1.1 200 OK
Content-Type: application/json
X-CM-Request-ID: gw_a1b2c3d4e5f6g7h8
X-CM-Cost: 0.0042
X-CM-Daily-Cost: 12.35
X-CM-Daily-Budget: 100.00
X-RateLimit-Limit: 300
X-RateLimit-Remaining: 297
X-RateLimit-Reset: 1709056860

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1709056800,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9,
    "total_tokens": 21
  }
}

HTTP/1.1 200 OK
Content-Type: text/event-stream
Cache-Control: no-cache
Connection: keep-alive
X-CM-Request-ID: gw_a1b2c3d4e5f6g7h8
X-CM-Cost: 0.0042
X-CM-Daily-Cost: 12.35
X-CM-Daily-Budget: 100.00

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709056800,"model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709056800,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709056800,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":"stop"}]}

data: [DONE]

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.curate-me.ai/v1/openai",
    default_headers={"X-CM-API-Key": "cm_sk_xxx"},
)
 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

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

POST /v1/messages

{
  "model": "claude-sonnet-4-20250514",
  "max_tokens": 1024,
  "messages": [
    {"role": "user", "content": "Hello, Claude!"}
  ]
}

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "claude-sonnet-4-20250514",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 12
  }
}

import anthropic
 
client = anthropic.Anthropic(
    base_url="https://api.curate-me.ai/v1/anthropic",
    default_headers={"X-CM-API-Key": "cm_sk_xxx"},
)
 
message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, Claude!"}],
)
print(message.content[0].text)

POST /v1/google/chat/completions

{
  "model": "gemini-2.5-flash",
  "messages": [
    {"role": "user", "content": "Explain quantum computing briefly."}
  ],
  "stream": false,
  "max_tokens": 256
}

{
  "id": "gw_a1b2c3d4e5f6g7h8",
  "object": "chat.completion",
  "created": 1709056800,
  "model": "gemini-2.5-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses quantum mechanical phenomena..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 45,
    "total_tokens": 53
  }
}

{
  "error": {
    "message": "Google Gemini is temporarily unavailable (circuit breaker open)",
    "type": "service_unavailable",
    "param": null,
    "code": "circuit_breaker_open"
  }
}

from openai import OpenAI
 
# Use Google Gemini via the OpenAI SDK
client = OpenAI(
    base_url="https://api.curate-me.ai/v1/google",
    default_headers={"X-CM-API-Key": "cm_sk_xxx"},
    api_key="your-google-api-key",  # passed as provider key
)
 
response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello from Gemini!"}],
)
print(response.choices[0].message.content)

POST /v1/deepseek/chat/completions

{
  "model": "deepseek-chat",
  "messages": [
    {"role": "user", "content": "What is deep learning?"}
  ],
  "stream": false
}

{
  "id": "chatcmpl-xyz789",
  "object": "chat.completion",
  "created": 1709056800,
  "model": "deepseek-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Deep learning is a subset of machine learning..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 7,
    "completion_tokens": 50,
    "total_tokens": 57
  }
}

from openai import OpenAI
 
# DeepSeek uses OpenAI-compatible format
client = OpenAI(
    base_url="https://api.curate-me.ai/v1/deepseek",
    default_headers={"X-CM-API-Key": "cm_sk_xxx"},
    api_key="your-deepseek-key",
)
 
response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello from DeepSeek!"}],
)
print(response.choices[0].message.content)

GET /v1/models

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 0,
      "owned_by": "openai",
      "description": "GPT-4o (latest)"
    },
    {
      "id": "gpt-4o-mini",
      "object": "model",
      "created": 0,
      "owned_by": "openai",
      "description": "GPT-4o Mini (budget)"
    },
    {
      "id": "claude-sonnet-4-20250514",
      "object": "model",
      "created": 0,
      "owned_by": "anthropic",
      "description": "Claude Sonnet 4"
    },
    {
      "id": "gemini-2.5-pro",
      "object": "model",
      "created": 0,
      "owned_by": "google",
      "description": "Gemini 2.5 Pro"
    },
    {
      "id": "deepseek-chat",
      "object": "model",
      "created": 0,
      "owned_by": "deepseek",
      "description": "DeepSeek Chat (V3)"
    }
  ]
}

{
  "error": {
    "message": "Model 'gpt-4o' is a openai model but was sent to the google endpoint. Use the correct endpoint.",
    "type": "invalid_request_error",
    "param": null,
    "code": "provider_mismatch"
  }
}

{
  "error": {
    "message": "Request body too large. Maximum size is 10485760 bytes (10 MB).",
    "type": "invalid_request_error",
    "param": null,
    "code": "request_too_large"
  }
}