Models and capabilities

Choose models by task type, latency tolerance, context size, and modality requirements like vision.

Model selection strategy

Use stronger models for architectural changes, complex refactors, and ambiguous tasks.
Use faster/cheaper models for short iterations, triage, and lightweight edits.
For visual tasks, select models that support vision capabilities.

Claude Sonnet 4.5: balanced reliability for everyday production work.
GPT-5.2 Codex: strong coding model for deep technical tasks.
Gemini 3 Flash: strong speed and helpful for design/UI iteration loops.
Kimi K2.5 and MiniMax M2.5: strong value picks for cost-conscious throughput.
Grok Code Fast 1: low-cost fast iteration when precision requirements are lower.

Defaults

Current defaults are Kimi K2.5 for free tier and Claude Sonnet 4.5 for paid tier.

Claude Sonnet 4.5: input $3, output $15, cached input $0.30, context 200k, vision support.
GPT-5.2 Codex: input $1.75, output $14, cached input $0.175, context 400k, vision support.
Gemini 3 Flash: input $0.5, output $3, cached input $0.05, context 1M, vision support.
Kimi K2.5: input $0.6, output $2.5, cached input $0.1, context 128k, vision support.
MiniMax M2.5: input $0.3, output $1.2, cached input $0.03, cache-creation input $0.38, context 205k.

Cost data changes over time

Use this as practical guidance, then confirm current values in-app before making strict budget decisions.