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-6 Sol OpenAI | Gemini 3.8 Flash Google | DeepSeek V4 Pro DeepSeek |
|---|---|---|---|
| Input $/1M | $2.00+167% | $0.75CHEAPEST | $1.32+76% |
| Cached input $/1M | $0.20+355% | $0.075+70% | $0.044CHEAPEST |
| Output $/1M | $10.00+167% | $3.75CHEAPEST | $3.96+6% |
| Blended $/1M (3:1) | $4.00+167% | $1.50CHEAPEST | $1.98+32% |
| Context window | 1.05MLARGEST | 1.05M−0% | 1M−5% |
| Capabilities | REASONINGVISIONTOOL USE | REASONINGVISIONAUDIO INPUTVIDEO INPUTTOOL USE | REASONINGTOOL USEOPEN WEIGHTS |
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