Skip to main content

​
Overview

Claude Code is Anthropic’s agentic coding tool that runs in your terminal. By routing Claude Code through Inworld Router, you get automatic failover, cost optimization, and unified observability — all without changing how you use Claude Code.

​
Why Route Claude Code Through Inworld Router?

  • Failover: If Anthropic is rate-limited or down, Inworld Router automatically fails over to another provider.
  • Cost control: Use model: "auto" with cost-optimized routing to reduce API spend on simpler coding tasks.
  • Observability: Track all Claude Code requests, token usage, and costs in the Inworld Portal.
  • Multi-model access: Use auto to let Inworld Router pick the best model, or route to OpenAI, Google, or other providers through the same Anthropic-compatible interface.

​
Setup

Claude Code uses the Anthropic SDK under the hood. Redirect it to Inworld Router by setting environment variables. Add these to your shell configuration file (e.g., ~/.zshrc or ~/.bashrc): 
export ANTHROPIC_BASE_URL=https://api.inworld.ai
export ANTHROPIC_AUTH_TOKEN=YOUR_INWORLD_API_KEY
ANTHROPIC_AUTH_TOKEN sends your key as Authorization: Bearer, which is how Inworld Router authenticates.
Then reload your shell and run Claude Code: 
source ~/.zshrc
claude
All requests from Claude Code will now route through Inworld Router.

​
Per-Session Override

For a quick test without changing your global config: 
ANTHROPIC_BASE_URL=https://api.inworld.ai \
ANTHROPIC_AUTH_TOKEN=YOUR_INWORLD_API_KEY \
  claude

​
Using Auto Routing

By default, Claude Code sends requests to a specific Claude model. With Inworld Router, you can override the model to use intelligent routing: 
claude --model auto
This lets Inworld Router select the best available model based on your routing configuration (cost, latency, or intelligence priorities).

​
Using a Specific Model

You can route to any model supported by Inworld Router: 
# Use a specific Anthropic model
claude --model anthropic/claude-opus-4-6

# Use an OpenAI model through the Anthropic interface
claude --model openai/gpt-5

# Use a Google model
claude --model google-ai-studio/gemini-2.5-flash

​
Using a Custom Router

If you’ve created a custom router (e.g., a cost-optimized or failover router), reference it by ID: 
claude --model inworld/failover-system

​
Comparison: Anthropic Direct vs Inworld Router

FeatureAnthropic DirectVia Inworld Router
Base URLhttps://api.anthropic.comhttps://api.inworld.ai
ModelsClaude models only50+ models across OpenAI, Google, Anthropic, Groq, and more
Auto routingNot availablemodel: "auto" with configurable sort criteria (cost, latency, intelligence)
Custom routersNot availablemodel: "inworld/your-router" with CEL conditions, variants, weights
FailoverNone — single providerAutomatic failover across providers
ObservabilityAnthropic ConsoleInworld Portal with routing metadata, attempt history, latency breakdown
Cost optimizationFixed pricingDynamic routing to cheaper models for simple tasks

​
Verifying the Setup

To confirm Claude Code is routing through Inworld Router, check the Inworld Portal’s Observability tab after making a request. You should see the request logged with routing metadata, including which model was selected and the latency breakdown.

​
Troubleshooting

​
”Unauthorized” errors

Ensure ANTHROPIC_AUTH_TOKEN is set to your Inworld API Key. You can find your API key in the Inworld Portal under Workspace Settings > Integrations.

​
Model not found

Ensure you’re using a valid model identifier:
  • auto — Inworld Router selects the best model
  • anthropic/claude-opus-4-6 — Specific model with provider/model format
  • inworld/your-router-id — Custom router

​
Connection issues

Verify the base URL is https://api.inworld.ai (no trailing slash, no path suffix).

​
Next Steps