Inference provider
AkashML
5 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
5
Median output speed
177 t/s
Median latency
324ms
Median price / 1M
$0.355
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
- GLM 5.2Z.ai52.6
- V4 Flash 0731DeepSeek51.8
- Qwen3.6 35B A3BQwen32.1
- Qwen3.5-35B-A3BQwen29.9
View as table
| Model | Intelligence |
|---|---|
| GLM 5.2 (Z.ai) | 52.6 |
| V4 Flash 0731 (DeepSeek) | 51.8 |
| Qwen3.6 35B A3B (Qwen) | 32.1 |
| Qwen3.5-35B-A3B (Qwen) | 29.9 |
Fastest output
Median tokens per second
- 234 t/s
- Qwen3.5-35B-A3BQwen203 t/s
- Qwen3.6 35B A3BQwen177 t/s
- V4 Flash 0731DeepSeek148 t/s
- GLM 5.2Z.ai142 t/s
View as table
| Model | Tokens/s |
|---|---|
| Llama 3.3 70B Instruct (Meta) | 234 |
| Qwen3.5-35B-A3B (Qwen) | 203 |
| Qwen3.6 35B A3B (Qwen) | 177 |
| V4 Flash 0731 (DeepSeek) | 148 |
| GLM 5.2 (Z.ai) | 142 |
Full catalogue
All 5 models on AkashML
Filter by creator
5 of 5 models| GLM 5.2 Z.aiopen | 52.6 | $0.23 |
| V4 Flash 0731 DeepSeekopen | 51.8 | $0.02 |
| Qwen3.6 35B A3B Qwenopen | 32.1 | $0.09 |
| Qwen3.5-35B-A3B Qwenopen | 29.9 | $0.09 |
| Llama 3.3 70B Instruct Metaopen | — | $0.01 |