Model Selection
PeopleClaw gives you access to 99+ AI models from leading providers including OpenAI, Anthropic, Google, and DeepSeek. Switch models anytime to find the best fit for your task.
How to Switch Models
In Telegram
Use the /model command:
/model— Browse available models with inline buttons/model claude-sonnet-4.5— Switch directly to a specific model/models— List all available models
In Web Dashboard
Use the model dropdown in the chat interface to select a model. You can search by name and filter by tier.
Model Tiers
Models are organized into 4 tiers based on capability and cost:
| Tier | Example Models | Best For |
|---|---|---|
| Flash | gemini-3-flash-preview, mimo-v2-flash, gpt-5-nano, glm-4.7-flash | Quick tasks, simple Q&A, drafts |
| Standard | gemini-3-flash-preview, GLM-5, kimi-k2.5, deepseek-v3.2, gpt-5-mini, claude-haiku-4.5 | Everyday tasks, writing, coding |
| Pro | gpt-5.2, gemini-3-pro-preview, claude-sonnet-4.5, claude-opus-4.5 | Complex analysis, research, nuanced writing |
| Premium | claude-opus-4.6, gpt-5.2-pro, grok-4 | Most demanding tasks, cutting-edge capabilities |
See Model Tiers for the full list and detailed comparison.
Recommendations by Use Case
- General chat & quick questions —
gemini-3-flash-preview(Standard, fast and cheap) ormimo-v2-flash(Flash, free) - Coding & technical tasks —
GLM-5(Standard, strong engineering) orkimi-k2.5(Standard, multimodal) - Complex reasoning —
deepseek-v3.2(Standard) orgpt-5.2(Pro) - Creative writing —
claude-sonnet-4.5(Pro) - Research & analysis —
gemini-3-pro-previeworclaude-opus-4.5(Pro) - Maximum quality —
claude-opus-4.6(Premium, SOTA) - Image generation —
nano-banana-pro(best for complex infographics) via/imagine
Tips
- You can switch models mid-conversation — the new model picks up the context
- Flash models don't count against your daily message limit for Standard+ tiers
- Try different models for the same task to compare quality