Inference provider
NextBit
7 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
7
Median output speed
50 t/s
Median latency
722ms
Median price / 1M
$0.172
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
No measurements available.
View as table
| Model | Intelligence |
|---|
Fastest output
Median tokens per second
- Gemma 4 26B A4B Google95 t/s
- Gemma 3 12BGoogle69 t/s
- ReMM SLERP 13BUndi9565 t/s
- Qwen3 14BQwen50 t/s
- Gemma 2 27BGoogle42 t/s
- Gemma 3 27BGoogle28 t/s
- Llama 3.3 Euryale 70BSao10K16 t/s
View as table
| Model | Tokens/s |
|---|---|
| Gemma 4 26B A4B (Google) | 95 |
| Gemma 3 12B (Google) | 69 |
| ReMM SLERP 13B (Undi95) | 65 |
| Qwen3 14B (Qwen) | 50 |
| Gemma 2 27B (Google) | 42 |
| Gemma 3 27B (Google) | 28 |
| Llama 3.3 Euryale 70B (Sao10K) | 16 |
Full catalogue
All 7 models on NextBit
Filter by creator
7 of 7 models| Gemma 4 26B A4B Googleopen | — | $0.03 |
| Qwen3 14B Qwenopen | — | $0.03 |
| Gemma 3 12B Googleopen | — | $0.006 |
| Gemma 3 27B Googleopen | — | $0.02 |
| Llama 3.3 Euryale 70B Sao10Kopen | — | $0.05 |
| Gemma 2 27B Googleopen | — | $0.05 |
| ReMM SLERP 13B Undi95open | — | $0.03 |