Repository navigation
Feature request: Auto-switch model based on input type (images) #32601
Description
Feature hasn't been suggested before.
- I have verified this feature I'm about to request hasn't been suggested before.
Describe the enhancement you want to request
Is your feature request related to a problem? Please describe.
When sending an image to opencode, it always uses the default model (e.g. mimo-v2.5-pro). If that model doesn't support vision/image input, the response is "I can't read images" even though a vision-capable model like mimo-v2-omni is available.
Describe the solution you'd like
Automatic model switching based on input content:
- If a message contains an image attachment → use a vision-capable model (configurable, e.g. xiaomi/mimo-v2-omni)
- Otherwise → use the default text model
Describe alternatives you've tried
- Plugin approach via chat.params hook - doesn't work (hook doesn't allow dynamic model switching)
- Manual switching via /model command - works but breaks flow
Additional context
This would be similar to how opencode-model-router handles task-based routing, but for input-type routing. Would be huge for multimodal workflows!
Metadata
Metadata
Assignees
Labels
No labels
Activity
github-actions commentedon Jun 16, 2026
This issue doesn't fully meet our contributing guidelines.
What needs to be fixed:
[FEATURE]:(e.g.[FEATURE]: Auto-switch model based on input type (images))Please edit this issue to address the above within 2 hours, or it will be automatically closed.
This issue might be a duplicate of existing issues. Please check:
If you believe this was flagged incorrectly, please let a maintainer know.
github-actions commentedon Jun 16, 2026
This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.
Feel free to open a new issue that follows our issue templates.