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 | MiMo-V2.5-Pro Xiaomi | DeepSeek V4 Flash DeepSeek | MiniMax M3 MiniMax |
|---|---|---|---|
| Input $/1M | $0.30CHEAPEST | $0.44+47% | $0.30CHEAPEST |
| Cached input $/1M | — | $0.014CHEAPEST | $0.06+329% |
| Output $/1M | $0.61CHEAPEST | $1.32+116% | $1.20+97% |
| Blended $/1M (3:1) | $0.377CHEAPEST | $0.66+75% | $0.525+39% |
| Context window | 1.05MLARGEST | 1M−5% | 1.05M−0% |
| Capabilities | REASONINGTOOL USEOPEN WEIGHTS | REASONINGTOOL USEOPEN WEIGHTS | REASONINGVISIONVIDEO INPUTTOOL 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