Text-only: MiMo-V2.5-Pro cannot process images in Gemini CLI and Codex

Quick fix

MiMo-V2.5-Pro is text-only. Use mimo-v2.5 instead, or a V2.6 model that supports images.

Symptom

Error outputCopy

CC-Switch并不将其识别为多模态，而是只支持text。

English translation

CC-Switch does not recognize it as multimodal; it only supports text.

Cause

This is not a cc-switch detection failure. MiMo-V2.5-Pro does not support image input, so cc-switch marks it as text-only based on the official model capabilities. Even if image capability is declared manually, the model will discard image content.

For image input, use a model that supports images. The report involved Windows, cc-switch 3.20.4, Gemini CLI, and Codex.

Fix

1. 1

   For the current Xiaomi MiMo provider, change the model from `mimo-v2.5-pro` to `mimo-v2.5`, which supports image input.

2. 2

   To use V2.6 models, upgrade to a prerelease starting with v4.0.0, then add the provider again from the Xiaomi MiMo or MiMo Token Plan preset, or manually add `mimo-v2.6-pro`, `mimo-v2.6-flash`, or `mimo-v2.6-pro-ultraspeed`. Providers created from older presets will not add these models automatically after upgrading.

Affected Versions

ToolGemini CLI, Codex

VersionUnknown

PlatformsWindows

Source Issues

This page is distilled from 1 real issues

• #7883Mimo-V2.5-Pro模型不支持图片

FAQ

(No FAQ yet)

Related problems

Codex provider writeback resets live UI settings from configUpgrade to cc-switch v4.0 or later. Provider switching updates only key fields and preserves the rest of ~/.codex/config.toml.7 issues mergedUnable to resolve apiKey and baseUrl variablesUse `{{ apiKey }}` or `{{baseUrl}}` in the custom usage query template and verify that `isValid: false` is treated as a failure.2 issues mergedPrompt files are never rebuiltPrompt, live configuration, and caches are not fully rebuilt after database restoration. No verifiable fix is available; follow the merged discussion.1 issues merged