Inference provider
Reka
9 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
9
Median output speed
124 t/s
Median latency
540ms
Median price / 1M
$0.73
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 5.3Z.ai44.8
- GLM 5.3 FlashZ.ai41.8
- V4 Pro 0423DeepSeek36.0
- V4 Flash 0731DeepSeek34.3
- Qwen3.8 27BQwen33.7
- Qwen3.5-27BQwen22.9
- Qwen3.6 27BQwen21.4
- Reka Flash 3Reka AI5.6
View as table
| Model | Intelligence |
|---|---|
| GLM 5.3 (Z.ai) | 44.8 |
| GLM 5.3 Flash (Z.ai) | 41.8 |
| V4 Pro 0423 (DeepSeek) | 36.0 |
| V4 Flash 0731 (DeepSeek) | 34.3 |
| Qwen3.8 27B (Qwen) | 33.7 |
| Qwen3.5-27B (Qwen) | 22.9 |
| Qwen3.6 27B (Qwen) | 21.4 |
| Reka Flash 3 (Reka AI) | 5.6 |
Fastest output
Median tokens per second
- Qwen3.8 27BQwen409 t/s
- V4 Flash 0731DeepSeek223 t/s
- GLM 5.3 FlashZ.ai141 t/s
- GLM 5.3Z.ai138 t/s
- Reka EdgeReka AI124 t/s
- Reka Flash 3Reka AI94 t/s
- V4 Pro 0423DeepSeek90 t/s
- Qwen3.5-27BQwen72 t/s
- Qwen3.6 27BQwen61 t/s
View as table
| Model | Tokens/s |
|---|---|
| Qwen3.8 27B (Qwen) | 409 |
| V4 Flash 0731 (DeepSeek) | 223 |
| GLM 5.3 Flash (Z.ai) | 141 |
| GLM 5.3 (Z.ai) | 138 |
| Reka Edge (Reka AI) | 124 |
| Reka Flash 3 (Reka AI) | 94 |
| V4 Pro 0423 (DeepSeek) | 90 |
| Qwen3.5-27B (Qwen) | 72 |
| Qwen3.6 27B (Qwen) | 61 |
Full catalogue
All 9 models on Reka
Filter by creator
9 of 9 models| GLM 5.3 Z.aiopen | 44.8 | $0.39 |
| GLM 5.3 Flash Z.aiopen | 41.8 | $0.05 |
| V4 Pro 0423 DeepSeekopen | 36.0 | $0.20 |
| V4 Flash 0731 DeepSeekopen | 34.3 | $0.05 |
| Qwen3.8 27B Qwenopen | 33.7 | $0.19 |
| Qwen3.5-27B Qwenopen | 22.9 | $0.22 |
| Qwen3.6 27B Qwenopen | 21.4 | $0.27 |
| Reka Flash 3 Reka AIopen | 5.6 | $0.02 |
| Reka Edge Reka AIopen | — | $0.008 |