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 | GPT-5.6 Terra OpenAI | Claude Sonnet 5 Anthropic | Gemini 3.7 Flash Google |
|---|---|---|---|
| Input $/1M | $2.00+167% | $2.00+167% | $0.75CHEAPEST |
| Cached input $/1M | $0.20+167% | $0.20+167% | $0.075CHEAPEST |
| Output $/1M | $12.00+220% | $10.00+167% | $3.75CHEAPEST |
| Blended $/1M (3:1) | $4.50+200% | $4.00+167% | $1.50CHEAPEST |
| Context window | 1.05MLARGEST | 1M−5% | 1.05M−0% |
| Capabilities | REASONINGVISIONTOOL USE | REASONINGVISIONTOOL USE | REASONINGVISIONAUDIO INPUTVIDEO INPUTTOOL 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