See tradeoffs side by side.
Compare up to four API models by cost, context, benchmark quality, and official links.
Anthropic
Claude Haiku 3.5
Fast Claude model for lightweight app flows and retrieval-heavy workloads.
Cheapestfull
Google Gemini
Gemini 2.5 Pro
Google’s top-tier reasoning and multimodal-capable API model for complex tasks.
Smartestfull
Google Gemini
Gemini 2.5 Flash
Google’s high-speed API model for lower-latency product flows and agents.
Cheapestfull
Direct comparison
Winners are highlighted row by row so cost, speed, and context tradeoffs are visible immediately.
| Metric | Claude Haiku 3.5 | Gemini 2.5 Pro | Gemini 2.5 Flash | Mistral Large |
|---|---|---|---|---|
| Provider | Anthropic | Google Gemini | Google Gemini | Mistral |
| Input / 1M | $0.80 | $1.25 | $0.30 | $0.50 |
| Output / 1M | $4 | $10 | $2.5 | $1.5 |
| Context window | 200K | 1M | 1M | 128K |
| Latency | 640 ms | 1500 ms | 520 ms | 920 ms |
| Intelligence | 77 | 94 | 81 | 86 |
| Coding | 73 | 90 | 76 | 84 |
| Best value score | 34.6 | 66.2 | 58.9 | 59.7 |
| Coverage | full | full | full | full |