Pick two or three models and see exactly how far apart they are — price per million tokens, context window, and what each one can actually do.
| METRIC | Gemini 3.1 Pro Google | GPT-5.6 Sol OpenAI | Claude Opus 5 Anthropic |
|---|---|---|---|
| Input $/1M | $2.00CHEAPEST | $4.00+100% | $5.00+150% |
| Cached input $/1M | $0.20CHEAPEST | $0.40+100% | $0.50+150% |
| Output $/1M | $12.00CHEAPEST | $20.00+67% | $25.00+108% |
| Blended $/1M (3:1) | $4.50CHEAPEST | $8.00+78% | $10.00+122% |
| Context window | 1.05M−0% | 1.05MLARGEST | 1M−5% |
| Capabilities | REASONINGVISIONAUDIO INPUTVIDEO INPUTTOOL USE | REASONINGVISIONTOOL USE | REASONINGVISIONTOOL USE |
Percentages are relative to the “best” value in each row — cheapest price, largest context. Blended assumes a typical 3:1 input-to-output token ratio.
ReqKey gives every API key a credit balance — validate, deduct, enforce limits, and see per-consumer spend in real time.
Start metering free