Free Tool
LLM Model Comparison
Context windows, pricing, and best-fit for the leading models — filter by provider.
| Model | Provider | Context | In / 1M | Out / 1M | Best for |
|---|---|---|---|---|---|
| Claude Opus | Anthropic | 200K+ | $15 | $75 | Hardest reasoning, agents, long docs |
| Claude Sonnet | Anthropic | 200K+ | $3 | $15 | Best all-round; coding & agents |
| Claude Haiku | Anthropic | 200K | $0.80 | $4 | Fast, cheap, high-volume tasks |
| GPT (flagship) | OpenAI | 128K+ | $2.50 | $10 | General-purpose, tooling ecosystem |
| GPT mini | OpenAI | 128K | $0.15 | $0.60 | Cheap classification & extraction |
| Gemini Pro | 1M+ | $1.25 | $5 | Huge context, multimodal | |
| Gemini Flash | 1M | $0.075 | $0.30 | Ultra-cheap, long-context, fast | |
| Llama (open) | Meta / self-host | 128K | self-host | self-host | On-prem, data residency, no per-token fee |
Prices are approximate public list prices (USD per 1M tokens) and change often — verify with each provider. We're model-agnostic and pick the best model per task on quality, latency & cost.