Fix common Claude Code & Codex API errors

The key never arrived or it's the wrong one. Check /status, re-copy the full key from the dashboard, and unset any leftover ANTHROPIC_API_KEY.

Check the url in the error to see where the request went, then define a custom provider with env_key and set that variable in the same environment Codex runs in.

Your available balance or today's subscription quota ran out. Top up, wait for the daily reset at midnight Beijing time, or — if you do have balance — retry in a few minutes.

Request-rate errors: raise the key's requests-per-minute or split traffic across keys. Concurrency errors: run fewer sessions or subagents at once — the limit is per account, so extra keys don't help.

The model ID is wrong — use an id from /api/v1/models (hyphenated). If every model fails and the response is an HTML page, your base URL is wrong instead.

A position in the millions means the body was truncated in transit: /compact or /clear, stop re-pasting big screenshots, read large files in chunks. A tiny position means the JSON itself is malformed.

CCSub already failed over between lines and none was free at that moment. Wait a minute and type "continue", or switch models with /model. Not billed, and not about your balance.

The upstream took too long to start answering. Use streaming (stream: true) in your own code, /compact very long contexts, and split long outputs. A one-off 504 just needs a retry and isn't billed.

The request never reached CCSub — usually a proxy variable pointing at a proxy that's off. Check env | grep -i proxy, unset it or add NO_PROXY for ccsub.net. Stuck on first launch? Edit ~/.claude.json.

The stream dropped before it finished. Make sure base_url is https://www.ccsub.net/api/v1, take local proxies out of the path, shorten very long turns, and raise stream_max_retries on the provider.