Skip to main content
If you are already using the Anthropic API directly, migrating to Inworld Router is a two-line change. Inworld Router supports the Anthropic Messages API natively, so your existing code, message format, and streaming logic all work as-is.

​
Key Differences

FeatureAnthropic DirectInworld Router
Base URLhttps://api.anthropic.comhttps://api.inworld.ai
AuthAnthropic API keyInworld API Key (Authorization: Bearer)
Model Namesclaude-opus-4-6anthropic/claude-opus-4-6 or auto
RoutingSingle providerMulti-provider with failover, cost optimization
ObservabilityAnthropic ConsoleInworld Portal (unified across all providers)

​
Migration Steps

​
1. Update Base URL and API Key

Python: 
import anthropic

client = anthropic.Anthropic(
    # From:
    # (default: https://api.anthropic.com)
    # api_key="sk-ant-..."
    # To:
    base_url="https://api.inworld.ai",
    auth_token="YOUR_INWORLD_API_KEY",  # Sends as Authorization: Bearer
)

# Everything else stays the same
message = client.messages.create(
    model="anthropic/claude-opus-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
TypeScript: 
import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  // From:
  // (default: https://api.anthropic.com)
  // apiKey: 'sk-ant-...'
  // To:
  baseURL: 'https://api.inworld.ai',
  authToken: 'YOUR_INWORLD_API_KEY',  // Sends as Authorization: Bearer
});
cURL: 
# From:
# curl https://api.anthropic.com/v1/messages -H "x-api-key: sk-ant-..."
# To:
curl --request POST \
  --url https://api.inworld.ai/v1/messages \
  --header 'Authorization: Bearer <your-inworld-api-key>' \
  --header 'anthropic-version: 2023-06-01' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "anthropic/claude-opus-4-6",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

​
2. Update Model Names

Add the anthropic/ prefix to model names:
  • claude-opus-4-6 → anthropic/claude-opus-4-6
  • claude-opus-4-20250514 → anthropic/claude-opus-4-20250514
  • claude-3-5-haiku-20241022 → anthropic/claude-3-5-haiku-20241022

​
3. Enable Intelligent Routing (Optional)

Instead of hardcoding a model, use Inworld Router’s intelligent routing: 
message = client.messages.create(
    model="auto",  # Inworld Router selects the best model
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Write a Python function to sort a list."}
    ]
)

​
What Stays the Same

  • Message format: messages array with role and content — identical.
  • Streaming: stream=True works the same way with Anthropic SSE events (message_start, content_block_delta, etc.).
  • System messages: Top-level system parameter works identically.
  • Tool use: Tool definitions, tool_use content blocks, and tool_result messages work identically.
  • max_tokens: Required parameter, same behavior.
  • temperature, top_p: Same behavior.
  • Multi-turn conversations: Same format, context is preserved correctly.

​
What You Gain

  1. Multi-Provider Failover: If Anthropic is down or rate-limited, Inworld Router automatically retries on OpenAI, Google, or other providers — and still returns the response in the Anthropic format.
  2. Cost Optimization: Route simple queries to cheaper models, reserve Claude for complex tasks.
  3. Cross-Provider Access: Use openai/gpt-5 or google-ai-studio/gemini-2.5-flash through the same Anthropic SDK — Inworld Router translates the request and returns an Anthropic-format response.
  4. Unified Observability: See all your LLM requests — across Anthropic, OpenAI, Google — in one dashboard.
  5. Custom Routing: Build routers with conditional logic, A/B testing, and weighted variants.

​
Environment Variables

If you use environment variables, update them: 
# From:
# export ANTHROPIC_API_KEY=sk-ant-...

# To:
export ANTHROPIC_AUTH_TOKEN=YOUR_INWORLD_API_KEY
export ANTHROPIC_BASE_URL=https://api.inworld.ai
export ANTHROPIC_API_KEY="" # Must be explicitly empty

​
Support

Need help with a complex migration? Contact our engineering team.