Claude Code Feature Availability
Which Claude Code features work with a QCode API key and which do not — each row labelled as measured or inferred
Claude Code Feature Availability¶
Part of Claude Code runs in the local CLI; another part is a hosted service tied to an Anthropic account. With a third-party API key (QCode included) the former works normally and the latter does not. This page draws the line so you do not spend an afternoon debugging.
About the evidence column: rows are marked measured (we actually ran it) or inferred (judged from how the product works, not tested). Do not treat inference as fact — if a row matters to you, verify it yourself.
The table¶
| Feature | With a QCode key | Evidence |
|---|---|---|
| CLI core: chat, file read/write, Bash, MCP, Skills, Plugins, subagents | ✅ | Measured: claude -p returns normally; file creation succeeds |
Permission mode bypassPermissions |
✅ | Measured: the same task wrote to disk |
Permission modes acceptEdits / manual / plan / dontAsk |
✅ | Inferred: local decision logic, no hosted classifier involved |
Permission mode auto |
❌ | Measured: under --permission-mode auto, Write and Bash were both denied; switching the same task on the same endpoint to bypassPermissions succeeded immediately (control) |
claude ultrareview / /ultrareview |
❌ | Measured: returns Ultrareview could not launch: Ultrareview is currently unavailable. |
claude setup-token |
❌ | Measured: the CLI's own help says requires Claude subscription |
| Cloud sessions / Claude Code on the web / mobile | ❌ | Inferred: account-side hosted services, not reached through an API key |
| Artifacts (publishing session output to claude.ai) | ❌ | Inferred: a claude.ai account feature |
| Self-hosted environments | ❌ | Inferred: a Team / Enterprise plan feature |
| Claude in Chrome extension | ❌ | Inferred: tied to an Anthropic plan |
| Claude Code Desktop (local sessions) | ⚠️ untested | Inferred: the desktop app drives the same local CLI and should inherit the same config |
Why auto mode does not work¶
auto mode relies on a hosted classifier to decide which actions may run unattended. With a
third-party key that classifier is unavailable, and the failure mode is not "allow everything" but
deny everything — Write and Bash are both blocked, down to a bare echo.
This is not specific to QCode; any third-party endpoint behaves the same. We ran the control:
same endpoint, same task, only --permission-mode changed from auto to bypassPermissions, and
the file was created immediately.
What to use instead: acceptEdits day to day (edits apply, commands still prompt), and
bypassPermissions in an isolated environment.
# day to day
claude --permission-mode acceptEdits
# isolated environment / CI (use with care)
claude --permission-mode bypassPermissions
Pointing Claude Code at QCode¶
export ANTHROPIC_BASE_URL="https://api.qcode.cc/api"
export ANTHROPIC_AUTH_TOKEN="cr_your_qcode_key"
claude -p "reply with exactly: OK"
OK means you are connected. See Environment Variables.
This table will go stale¶
Claude Code ships weekly and the boundary moves. If you observe behaviour that contradicts this page, trust your own measurement, and please tell us at hi@qcode.cc so we can update it.