§.FAQ

Which LLM model should I pick?

Decision matrix: speed vs quality vs cost for each supported model.

Updated 2026-04-13 · By Jon Lasley
Use caseTop pickRunner-up
Complex reasoning, long context, highest qualityClaude Opus 4.7GPT-5.5 or Claude Opus 4.6
Most general-purpose prompt workClaude Sonnet 4.6GPT-4.1 or GPT-5.4
Fast, cheap, high volumeClaude Haiku 4.5GPT-4.1 Nano or Gemini 2.5 Flash-Lite
Multi-modal (images, audio)Gemini 2.5 ProClaude Sonnet 4.6 (images only)
Cost-optimized inference at scaleGemini 2.5 Flash-LiteGPT-4.1 Nano
Hardest reasoning problemsGPT-5.5 (or GPT-5.5 Pro)Claude Opus 4.7 or Gemini 2.5 Pro
Reasoning at low costGPT-5.4 MiniGPT-5.4 Nano
Coding-task promptsGPT-5.3 CodexGPT-5.4 or Claude Opus 4.7
Latency-criticalClaude Haiku 4.5GPT-4.1 Mini or Gemini 2.5 Flash-Lite
Experiment in the playground
Two paths in the playground: switch the model dropdown and re-run sequentially (each run recorded in test-run history with latency / tokens / cost), or click Compare models to run the same prompt against 2–5 models in parallel and see outputs, costs, and latencies side-by-side. With a judge step you can also score every model's output against a shared rubric and surface the best per criterion. See Comparing models in the playground.