Skip to main content
Pick a model that matches your task. You can switch models at any time before sending a message.
Model picker in the SteerCode composer

Select a model before you send your message

​
Available models

ModelProviderProfileThinking/ReasoningCredit usage
GPT-5OpenAIMost advanced coding model✅ Deep multi-step reasoningPremium (credits)
GPT-4.1OpenAIFast senior programmer–Premium (credits)
GPT-4.1 miniOpenAIFast junior programmer–Basic (no credits)
Gemini 2.0 FlashGoogleFast junior programmer–Basic (no credits)
Claude Sonnet 3.7 / 4AnthropicStrong quality-speed balance✅Premium (credits)
Claude Opus 4AnthropicHighest-quality reasoning✅Premium (credits)
You may occasionally see experimental / stealth models (e.g., Horizon Alpha). Availability changes—watch our socials for announcements.
If you’re iterating rapidly or doing light edits, choose a Basic model to avoid credit usage. Switch to a Premium model for complex refactors, tricky bugs, or multi-step integrations.

​
Quick guidance

  • Speed first (UI copy, small edits, quick prompts): GPT-4.1 mini or Gemini Flash 2.0
  • General coding (features, refactors, tests): GPT-4.1 or Claude Sonnet
  • Hard tasks (deep reasoning, multi-file migrations): GPT-5 or Claude Opus
Thinking-enabled models (e.g., GPT-5, Sonnet/Opus) are slower and consume more credits. Use them when the extra reasoning matters.