Claude Code

Configure Claude Code for your enterprise and verify the request in your console logs.

Configuration

Use your enterprise HTTPS gateway URL, an API key scoped to this tool and a model ID that supports the protocol. The address below comes from this gateway’s public configuration. Find an eligible model

  1. Confirm your enterprise channel offers a Claude model with Messages support and meets Anthropic’s Claude Code gateway requirements.
  2. Inject TOKEN_PYXIS_API_KEY with your enterprise secret manager. Replace the gateway URL and model ID below, then launch Claude Code in the same terminal.
  3. For persistent settings, save ANTHROPIC_BASE_URL and ANTHROPIC_MODEL under env in ~/.claude/settings.json. Continue injecting the credential through your secret manager.
API protocolAddress to enter
Anthropic MessagesBase URLhttps://tokenpyxis.com
export ANTHROPIC_BASE_URL="https://tokenpyxis.com"
export ANTHROPIC_AUTH_TOKEN="$TOKEN_PYXIS_API_KEY"
export ANTHROPIC_MODEL="YOUR_ELIGIBLE_CLAUDE_MODEL_ID"
claude

Verification

Run /status in Claude Code to check the Anthropic base URL and credential source. Send a text request in a new session and confirm the model in enterprise logs.

Check the model, timestamp and token usage in the enterprise console logs. If the tool shows a request ID, look it up directly. See reconciliation steps

Troubleshooting

For 401, check ANTHROPIC_AUTH_TOKEN and the gateway URL. Validate features that require a separate /v1/messages/count_tokens endpoint independently.

Business inquiries
Scan with WeChat to add the business team on WeCom