AI Gateway

response = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a Python function to calculate fibonacci numbers."},
        {"role": "assistant", "content": "Here's a fibonacci function:\n\n```python\ndef fib(n):\n    if n <= 1:\n        return n\n    return fib(n-1) + fib(n-2)\n```"},
        {"role": "user", "content": "Can you make it iterative for better performance?"},
    ],
    temperature=0.7,
    max_tokens=500,
)

response = client.chat.completions.create(
    model="gemini-2.5-pro",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe what you see in this image."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/photo.jpg"
                    },
                },
            ],
        }
    ],
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Compare these two screenshots. What changed?"},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{before_image}"},
                },
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{after_image}"},
                },
            ],
        }
    ],
)

# Let the model decide (default)
tool_choice="auto"

# Force the model to call a tool
tool_choice="required"

# Force a specific tool
tool_choice={"type": "function", "function": {"name": "get_weather"}}

# Don't use tools (even if provided)
tool_choice="none"

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The quick brown fox jumps over the lazy dog",
)

embedding = response.data[0].embedding
print(f"Dimensions: {len(embedding)}")

{
  "object": "list",
  "data": [
    { "id": "gpt-4o", "object": "model", "owned_by": "openai" },
    { "id": "claude-sonnet-4-20250514", "object": "model", "owned_by": "anthropic" },
    { "id": "gemini-2.5-pro", "object": "model", "owned_by": "google" }
  ]
}

curl https://your-temps-instance.com/api/ai/v1/chat/completions \
  -H "Authorization: Bearer your-temps-api-key" \
  -H "x-provider-api-key: sk-your-own-openai-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

curl https://your-temps-instance.com/api/ai/v1/chat/completions \
  -H "Authorization: Bearer your-temps-api-key" \
  -H "x-provider-api-key: sk-your-own-openai-key" \
  -H "x-provider-base-url: https://your-proxy.example.com/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI
import httpx

# Pass extra headers via the OpenAI client
client = OpenAI(
    base_url="https://your-temps-instance.com/api/ai/v1",
    api_key="your-temps-api-key",
    default_headers={
        "x-conversation-id": "conv-abc123",
        "x-tags": "production,chat-feature",
    },
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)

curl https://your-temps-instance.com/api/ai/v1/chat/completions \
  -H "Authorization: Bearer your-temps-api-key" \
  -H "x-conversation-id: conv-abc123" \
  -H "x-tags: production,chat-feature" \
  -H "x-request-id: req-xyz789" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

[
  {
    "id": 1,
    "provider": "openai",
    "display_name": "Production OpenAI Key",
    "api_key_masked": "***",
    "base_url": null,
    "is_active": true,
    "created_at": "2025-01-15T10:00:00Z",
    "updated_at": "2025-01-15T10:00:00Z"
  }
]

{
  "success": true,
  "provider": "anthropic",
  "latency_ms": 342,
  "error": null
}

{
  "entries": [
    {
      "provider": "anthropic",
      "model": "claude-sonnet-4-20250514",
      "input_tokens": 842,
      "output_tokens": 311,
      "latency_ms": 1240,
      "estimated_cost_microcents": 7184,
      "status": 200,
      "is_streaming": true,
      "is_byok": false,
      "conversation_id": "conv-abc123",
      "tags": "production,chat-feature",
      "request_id": "req-xyz789",
      "trace_id": null
    }
  ],
  "total": 1284
}

[
  {
    "conversation_id": "conv-abc123",
    "message_count": 12,
    "total_input_tokens": 8432,
    "total_output_tokens": 3210,
    "total_tokens": 11642,
    "total_cost_microcents": 58210,
    "avg_latency_ms": 824.5,
    "models_used": ["gpt-4o", "claude-sonnet-4-20250514"],
    "first_at": "2025-01-15T09:00:00Z",
    "last_at": "2025-01-15T09:45:00Z"
  }
]

{
  "models": [
    {
      "model": "gpt-4o",
      "display_name": "GPT-4o",
      "provider": "openai",
      "input_per_million": 2.50,
      "output_per_million": 10.00,
      "cache_hit_per_million": 1.25,
      "batch_input_per_million": 1.25,
      "batch_output_per_million": 5.00,
      "deprecated": false
    },
    {
      "model": "claude-sonnet-4-20250514",
      "display_name": "Claude Sonnet 4.6",
      "provider": "anthropic",
      "input_per_million": 3.00,
      "output_per_million": 15.00,
      "cache_write_5m_per_million": 3.75,
      "cache_hit_per_million": 0.30,
      "deprecated": false
    }
  ]
}