§.FAQ
Which LLM model should I pick?
Decision matrix: speed vs quality vs cost for each supported model.
Updated 2026-04-13
| Use case | Top pick | Runner-up |
|---|---|---|
| Complex reasoning, long context, highest quality | Claude Opus 4.6 | GPT-5 (reasoning) |
| Most general-purpose prompt work | Claude Sonnet 4.6 | GPT-4.1 |
| Fast, cheap, high volume | Claude Haiku 4.5 | GPT-4.1 Mini or Nano |
| Multi-modal (images, audio) | Gemini 2.5 Pro | Claude Sonnet 4.6 (images only) |
| Cost-optimized inference at scale | GPT-4.1 Nano | Gemini 2.5 Flash |
| Hardest reasoning problems | OpenAI o3 | Gemini 2.5 Pro with thinking enabled |
| Latency-critical | Claude Haiku 4.5 | GPT-4.1 Mini |
Experiment in the playground
The playground's compare mode runs two models side-by-side with the same prompt. Pick a representative test case, run it against a few candidates, and use the latency / token / cost output to decide. The playground's test-run history keeps the comparisons available for later review.