Skip to content
CC Switch WikiUnofficial Community Wiki

“Image generation is not enabled for this group” error - CC Switch

Quick fix

Manually filter image generation requests or configure a local bridge process to read response headers to work around the 403 block.

Symptom

Section titled “Symptom”
Error output
status_code=403, Image generation is not enabled for this group

Cause

Section titled “Cause”

This issue is mainly caused by two types of relay restrictions. First, newer tools such as Codex include image generation parameters in chat requests by default, but most relays do not support direct calls to image generation APIs. The upstream service then returns 403 and reports that image generation is not enabled.

Second, some relays, such as LiteLLM Proxy, issue restricted virtual keys that allow inference routes only. Management and billing endpoints such as /key/info are blocked with 403. For these keys, quota information is available only in the HTTP response headers of regular inference requests. However, CC Switch checks the status code before calling the usage query extractor. For any non-2xx response, it stops and discards the response headers, so a script alone cannot retrieve quota data. The community has not agreed on a single fix. Issue #4938 proposes an image generation filter toggle, while #5227 proposes allowing the extractor to read response headers; neither change has been merged.

Fix

Section titled “Fix”

  1. If your relay supports image generation filtering, enable the image parameter filtering option in the cc-switch configuration to avoid sending image generation instructions to unsupported models.

  2. For quota query 403 errors caused by restricted keys, you can run a local bridge process. Have it send a probe request, read quota fields from the HTTP response headers, convert them to a JSON body, and provide that to CC Switch for querying. This works around the native extractor limitation.

Affected Versions

Section titled “Affected Versions”
ToolCodex / Claude Code
VersionUnknown
PlatformsUnknown

Source Issues

Section titled “Source Issues”

This page is distilled from 2 real issues

FAQ

Section titled “FAQ”
Why do I still get 403 errors after enabling a local proxy?
Some relay 403 errors occur at the inference endpoint itself, for example because image generation parameters are unsupported, or because key permissions restrict management endpoints. A local proxy only forwards traffic; it cannot change the upstream gateway’s authentication logic or parameter validation rules.
How can I check the remaining quota for a restricted key without running a background process?
The current version of CC Switch stops on non-2xx responses and discards the response headers, so it cannot read the quota directly. Wait for the response header passthrough feature to be merged (see #5227), or temporarily use a local bridge script to persist the header data as JSON for the extractor to read.
Section titled “Related problems”
Tray menu does not show current Plan allowance when multiple ChatGPT accounts are linked - CodexUpgrade cc-switch: the tray menu failing to show allowance with multiple linked ChatGPT accounts is a confirmed bug, fixed in commit e53ab21 and released…3 issues mergeddeepseek接入 模型勾选了1m: no 1M context option in Claude Code model pickerUpgrade cc-switch to v3.17.0+, leave the DeepSeek provider's ANTHROPIC_MODEL empty or check 1M there too, fill only Haiku/Sonnet/Opus mappings… (Claude Code)7 issues mergedUsage query requires same-origin requests in cc-switchIn cc-switch, switch to the generic or custom template and enter the usage query URL directly in the request address to bypass the same-origin restriction.4 issues merged

This is an unofficial community wiki with no affiliation to the cc-switch authors or the project itself. Its content is compiled from the project's public GitHub issues. This site distributes no software.