Inference provider
NextBit
8 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
8
Median output speed
51 t/s
Median latency
454ms
Median price / 1M
$0.399
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
- Qwen3.5-35B-A3BQwen29.9
View as table
| Model | Intelligence |
|---|---|
| Qwen3.5-35B-A3B (Qwen) | 29.9 |
Fastest output
Median tokens per second
- Qwen3.5-35B-A3BQwen203 t/s
- Gemma 4 26B A4B Google71 t/s
- UnslopNemo 12BTheDrummer62 t/s
- Qwen3 14BQwen51 t/s
- ReMM SLERP 13BUndi9551 t/s
- MythoMax 13BGryphe51 t/s
- Gemma 2 27BGoogle27 t/s
- Llama 3.3 Euryale 70BSao10K8 t/s
View as table
| Model | Tokens/s |
|---|---|
| Qwen3.5-35B-A3B (Qwen) | 203 |
| Gemma 4 26B A4B (Google) | 71 |
| UnslopNemo 12B (TheDrummer) | 62 |
| Qwen3 14B (Qwen) | 51 |
| ReMM SLERP 13B (Undi95) | 51 |
| MythoMax 13B (Gryphe) | 51 |
| Gemma 2 27B (Google) | 27 |
| Llama 3.3 Euryale 70B (Sao10K) | 8 |
Full catalogue
All 8 models on NextBit
Filter by creator
8 of 8 models| Qwen3.5-35B-A3B Qwenopen | 29.9 | $0.09 |
| Gemma 4 26B A4B Googleopen | — | $0.03 |
| Qwen3 14B Qwenopen | — | $0.08 |
| Llama 3.3 Euryale 70B Sao10Kopen | — | $0.05 |
| UnslopNemo 12B TheDrummeropen | — | $0.03 |
| Gemma 2 27B Googleopen | — | $0.05 |
| ReMM SLERP 13B Undi95open | — | $0.04 |
| MythoMax 13B Grypheopen | — | $0.007 |