Choose the reasoning model independently in the main flowmo assistant, Flowgen Agent, and scoped code/interactive chats, with current capability and Flowie cost shown from the shared catalog.
Where: Open an AI chat → Model picker
Before you start
- Open the specific chat surface whose next turn you want to configure.
Key ideas
- Shared catalog: Every picker resolves labels, providers, capabilities, and pricing from the same versioned language-model catalog.
- Per-chat choice: The selected model belongs to that chat surface and is sent as the requested model for the next turn.
- Visible cost: Higher-capability models can cost more Flowies per turn; the pricing catalog shows the exact tier.
Steps
- Open the chat you want to use.
- Open its model picker.
- Choose the model that fits the task and budget.
- Send the next message; the selection persists for that chat context.
Model choice is per chat surface
- Main website/video assistant.
- Flowgen Agent conversation.
- Scoped interactive/code element chat.
- Other surfaces that expose the shared model picker.
Choose by work, not rank alone
- Use a lower-cost fast model for narrow mechanical actions and short iterations.
- Use stronger reasoning for architecture, multi-stage planning, difficult diagnosis, or design decisions.
- Check modality/context requirements before attaching large documents or media.
MCP hosts are separate
An external MCP host uses the model selected in that host. Changing Flowgen’s in-app model does not change Claude/Codex, and the MCP host should not proxy the task into Flowgen just to use that picker.
August 31 model additions and compatibility
GLM 5.3 Flash is a distinct multimodal language-model route with native image/video input and mandatory reasoning. Gemini 3.5/3.6/3.7 Flash are retired from pickers; updated clients resolve saved selections to Gemini 3.8 Flash. Historical catalog labels remain available for old runs, and the base flash round tier is unchanged.
- Wan 3.0 and Prime support frame, reference, and extend workflows with source-video billing and explicit duration limits.
- Omni 1.1 Flash adds 360p/720p/1080p/4K, up to ten images and three videos of at most ten seconds each, last-frame support, and continuation.
- Grok Imagine 2 Standard costs 3/5 Sparks at 1K/2K; Quality costs 5/6.
- GPT Image 2 supported output sizes are flat-priced: generation 20 Sparks, edit route 22.
- OpenRouter attachments follow catalog capabilities. PDFs/Markdown are prepared as document content instead of being reduced to unreadable URLs.
- OpenRouter agent streaming and increased output ceilings support longer answers; output remains bounded and is included in usage-based billing.
Tips
- Compare the exact current Flowie row; model catalogs and rates can change.
- Keep one chat on one goal so model history and attachments remain relevant.
Limitations and important notes
- A selected model may be unavailable when provider health, plan, or task capabilities change.
- The displayed base turn price may not include every separately priced media generation or long-context action.
Troubleshooting
A different model answered than expected
Confirm the picker in the exact chat surface, because main assistant, Flowgen Agent, scoped chats, and an external MCP host keep separate model selections.
Related guides
- Model pricing in Flowies
- Flowgen image, video & text model catalog
- Flowmo pricing and Flowies: the overview
- Flowmo AI Assistant: Smart Router & Agents Guide
- MCP host AI and flowmo AI: who does what
- GLM 5.3 Flash: multimodal chat, reasoning, and pricing
- Wan 3.0 and Prime: video modes, references, and controls
- Gemini Omni 1.1 Flash: generate, reference, edit, and extend video
- Grok Imagine 2: Standard, Quality, resolution, and image edits