Anthropic Drop-in

Base URL

https://gateway.metrixllm.com/anthropic

Quick setup

import anthropic

client = anthropic.Anthropic(
    base_url="https://gateway.metrixllm.com/anthropic",
    api_key="sk-metrix-YOUR_API_KEY"
)

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
)
print(message.content[0].text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
    baseURL: "https://gateway.metrixllm.com/anthropic",
    apiKey: "sk-metrix-YOUR_API_KEY"
});

const message = await client.messages.create({
    model: "claude-sonnet-4-20250514",
    max_tokens: 1024,
    messages: [{ role: "user", content: "Hello!" }]
});
console.log(message.content[0].text);

curl -X POST https://gateway.metrixllm.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-metrix-YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Do not use your Anthropic API key. The gateway authenticates with MetrixLLM keys (sk-metrix-* prefix), then uses its own provider keys (or your BYOK keys) to call Anthropic.

Request Headers

Every request supports these headers for authentication, tracing, and metadata:

Header	Type	Required	Description
`x-api-key`	`string`	Yes*	`sk-metrix-{key}` — MetrixLLM API key
`Authorization`	`string`	Yes*	`Bearer sk-metrix-{key}` — alternative to `x-api-key`
`Content-Type`	`string`	Yes	Must be `application/json`
`anthropic-version`	`string`	No	Anthropic API version (e.g. `2023-06-01`). Forwarded to upstream.

Session Tracing

Header	Description	Stored In
`metrix-session-id`	Unique session identifier — groups related requests into a traceable session	`workspace_logs.session_id`
`metrix-parent-id`	Links a request to a parent span in the session trace	`workspace_logs.parent_id`
`metrix-session-name`	Human-readable name for the span (for dashboard display)	`workspace_logs.span_name`

Custom Properties Attach up to 10 custom metadata properties per request:

Header Pattern	Description
`metrix-property-{key}`	Custom metadata property. Used for rate limit targeting, analytics, and filtering.

Example: metrix-property-team: engineering, metrix-property-environment: production IP Detection

Header	Description
`x-forwarded-for`	Client IP address (first IP in comma-separated list)
`x-real-ip`	Fallback client IP header
`cf-ipcountry`	Cloudflare country code of the connecting client

Supported models

Model	ID
Claude Sonnet 4	`claude-sonnet-4-20250514`
Claude 3.5 Haiku	`claude-3-5-haiku-20241022`

Routing mode

Control how the gateway authenticates with Anthropic using the mode parameter:

Mode	Behavior	Balance deduction
`"auto"` (default)	Uses your BYOK key if configured, otherwise falls back to platform key	BYOK: none. Native: yes
`"byok"`	Forces your own Anthropic API key (from workspace settings)	None — your key, your cost
`"native"`	Forces MetrixLLM’s platform key	Yes — deducted from workspace credits

# Use your own Anthropic key (BYOK) — never deducts workspace credits
message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    mode="byok",
    messages=[{"role": "user", "content": "Hello!"}]
)

const message = await client.messages.create({
    model: "claude-sonnet-4-20250514",
    max_tokens: 1024,
    mode: "byok",
    messages: [{ role: "user", content: "Hello!" }]
});

curl -X POST https://gateway.metrixllm.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-metrix-YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "mode": "byok",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

When mode is omitted (or "auto"), the gateway prefers your BYOK key if one is configured. If your workspace has insufficient credits and you have a BYOK key, the gateway automatically uses it instead of failing with a payment error.

Web search

Web search mode (default)

Add "web_search": true to your request. The gateway performs a web search, generates optimized search queries, and injects the results into your system prompt.

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    web_search=True,
    messages=[{"role": "user", "content": "What happened in the news today?"}]
)

const message = await client.messages.create({
    model: "claude-sonnet-4-20250514",
    max_tokens: 1024,
    web_search: true,
    messages: [{ role: "user", content: "What happened in the news today?" }]
});

curl -X POST https://gateway.metrixllm.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-metrix-YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "web_search": true,
    "messages": [{"role": "user", "content": "What happened in the news today?"}]
  }'

Parameters:

Parameter	Type	Default	Description
`web_search`	`boolean`	`false`	Set to `true` to enable web search
`web_search_level`	`string`	`"medium"`	`"low"` (1 query, 3 results), `"medium"` (2 queries, 5 results), `"high"` (3 queries, 8 results)
`web_search_lang`	`string`	`"en"`	Search language (ISO code)
`web_search_country`	`string`	`"us"`	Search country (ISO code)

Native mode

Set "web_search": "native" to use Anthropic’s built-in web search. The gateway adds the web_search_20250305 tool to your request.

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    web_search="native",
    web_search_max_uses=5,
    messages=[{"role": "user", "content": "What's the latest AI news?"}]
)

const message = await client.messages.create({
    model: "claude-sonnet-4-20250514",
    max_tokens: 1024,
    web_search: "native",
    web_search_max_uses: 5,
    messages: [{ role: "user", content: "What's the latest AI news?" }]
});

curl -X POST https://gateway.metrixllm.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-metrix-YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "web_search": "native",
    "web_search_max_uses": 5,
    "messages": [{"role": "user", "content": "What'\''s the latest AI news?"}]
  }'

Native-specific parameters:

Parameter	Type	Description
`web_search_max_uses`	`integer`	Maximum number of search queries Anthropic can make

In native mode, Anthropic handles search internally using its own web_search_20250305 tool. The gateway adds this tool to your tools array automatically — you don’t need to define it yourself.

Extended thinking

Claude supports extended thinking for complex reasoning tasks:

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=16000,
    thinking={
        "type": "enabled",
        "budget_tokens": 10000
    },
    messages=[{"role": "user", "content": "Solve this step by step: what is 2^10 + 3^5?"}]
)

Tool use

tools = [
    {
        "name": "get_weather",
        "description": "Get current weather for a location",
        "input_schema": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "City name"}
            },
            "required": ["location"]
        }
    }
]

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    tools=tools,
    messages=[{"role": "user", "content": "What's the weather in London?"}]
)

Streaming

with client.messages.stream(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Tell me a story"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Prompt management

Reference a stored prompt template by ID:

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    prompt_id="your-prompt-uuid",
    inputs={"user_name": "Alice"},
    messages=[{"role": "user", "content": "Hello!"}]
)

Custom properties

Attach metadata for analytics and rate limit targeting:

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
    extra_headers={
        "metrix-property-team": "backend",
        "metrix-property-env": "production",
        "metrix-session-id": "session_abc123"
    }
)

Response headers

Every response includes these headers:

Header	Description
`Content-Type`	Always `application/json`
`X-Metrix-Provider`	Provider that served the request (e.g. `anthropic`, `openai`, `google`)
`X-Metrix-Model`	Exact model used for the request
`X-Metrix-Cache-Status`	`"HIT"` or `"miss"` (semantic cache)
`X-Metrix-Retry-Count`	Number of retry attempts (0 if none)
`X-Metrix-Retry-Status`	`"success"`, `"failed"`, or `"not_triggered"`
`X-Metrix-Fallback`	`"true"` if a fallback provider was used (only when applicable)
`X-RateLimit-Limit`	Configured limit for the rate window
`X-RateLimit-Remaining`	Remaining quota in the current window
`X-RateLimit-Requests-Remaining`	Remaining requests in current window
`X-RateLimit-Tokens-Remaining`	Remaining tokens in current window

On cache HIT responses, only Content-Type and X-Metrix-Cache-Status: HIT are returned. On rate limited responses (429 Too Many Requests):

Header	Description
`Retry-After`	Seconds to wait before retrying
`X-RateLimit-{type}-Limit`	Maximum limit (e.g. `X-RateLimit-rpm-Limit`, `X-RateLimit-tpm-Limit`)
`X-RateLimit-{type}-Remaining`	Remaining count in the current window
`X-RateLimit-Reset`	Seconds until the rate window resets

Overview

Connect

Build

Observe

Optimize

Manage

Gateway API Reference

Base URL

Quick setup

Request Headers

Supported models

Routing mode

Web search

Web search mode (default)

Native mode

Extended thinking

Tool use

Streaming

Prompt management

Custom properties

Response headers

​Base URL

​Quick setup

​Request Headers

​Supported models

​Routing mode

​Web search

​Web search mode (default)

​Native mode

​Extended thinking

​Tool use

​Streaming

​Prompt management

​Custom properties

​Response headers

Base URL

Quick setup

Request Headers

Supported models

Routing mode

Web search

Web search mode (default)

Native mode

Extended thinking

Tool use

Streaming

Prompt management

Custom properties

Response headers