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 | Claude Fable 5.1 Anthropic | GPT-6 Astra OpenAI | Gemini 3.1 Pro Google |
|---|---|---|---|
| Input $/1M | $10.00+400% | $10.00+400% | $2.00CHEAPEST |
| Cached input $/1M | $0.25+25% | $1.00+400% | $0.20CHEAPEST |
| Output $/1M | $50.00+317% | $50.00+317% | $12.00CHEAPEST |
| Blended $/1M (3:1) | $20.00+344% | $20.00+344% | $4.50CHEAPEST |
| Context window | 1M−5% | 1.05MLARGEST | 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