NextBit
Inference providernextbit256.com ↗
Models on NextBit · prices & measurements for models served by NextBit’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
 Gemma 3 12BGoogleBEST PRICE | $0.05 | $0.15 | 131K | int4 | — | — | — | cheapest here |
| Gemma 4 26B A4B Google | $0.076 | $0.255 | 262K | bf16 | 1.2s° | 87° tok/s | 5/5 | $0.042 elsewhere |
 Qwen3 14BQwenBEST PRICE | $0.10 | $0.22 | 41K | int4 | 4.4s° | 66° tok/s | — | cheapest here |
| UNReMM SLERP 13BUndi95 | $0.45 | $0.65 | 6K | bf16 | 0.77s° | 27° tok/s | — | $0.35 elsewhere |
 Llama 3.3 Euryale 70BSao10K | $0.65 | $0.75 | 131K | bf16 | 22.5s° | 12° tok/s | — | only provider |
| Gemma 2 27BGoogle | $0.65 | $0.65 | 8K | int4 | 1.6s° | 61° tok/s | — | only provider |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for NextBit’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page