Inference provider
Fireworks
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
116 t/s
Median latency
354ms
Median price / 1M
$0.508
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
- Kimi K3Moonshot AI59.7
- GLM 5.2Z.ai52.6
- V4 Flash 0731DeepSeek51.8
- V4 Flash 0423DeepSeek51.8
- V4 ProDeepSeek45.3
- Kimi K2.6Moonshot AI45.1
- M2.7MiniMax38.9
- gpt-oss-20bOpenAI15.2
View as table
| Model | Intelligence |
|---|---|
| Kimi K3 (Moonshot AI) | 59.7 |
| GLM 5.2 (Z.ai) | 52.6 |
| V4 Flash 0731 (DeepSeek) | 51.8 |
| V4 Flash 0423 (DeepSeek) | 51.8 |
| V4 Pro (DeepSeek) | 45.3 |
| Kimi K2.6 (Moonshot AI) | 45.1 |
| M2.7 (MiniMax) | 38.9 |
| gpt-oss-20b (OpenAI) | 15.2 |
Fastest output
Median tokens per second
- M2.7MiniMax307 t/s
- gpt-oss-20bOpenAI252 t/s
- V4 Flash 0731DeepSeek148 t/s
- GLM 5.2Z.ai142 t/s
- Kimi K2.6Moonshot AI89 t/s
- V4 Flash 0423DeepSeek87 t/s
- Kimi K3Moonshot AI71 t/s
- V4 ProDeepSeek71 t/s
View as table
| Model | Tokens/s |
|---|---|
| M2.7 (MiniMax) | 307 |
| gpt-oss-20b (OpenAI) | 252 |
| V4 Flash 0731 (DeepSeek) | 148 |
| GLM 5.2 (Z.ai) | 142 |
| Kimi K2.6 (Moonshot AI) | 89 |
| V4 Flash 0423 (DeepSeek) | 87 |
| Kimi K3 (Moonshot AI) | 71 |
| V4 Pro (DeepSeek) | 71 |
Full catalogue
All 8 models on Fireworks
Filter by creator
8 of 8 models| Kimi K3 Moonshot AIopen | 59.7 | $1.35 |
| GLM 5.2 Z.aiopen | 52.6 | $0.23 |
| V4 Flash 0731 DeepSeekopen | 51.8 | $0.02 |
| V4 Flash 0423 DeepSeekopen | 51.8 | $0.02 |
| V4 Pro DeepSeekopen | 45.3 | $0.09 |
| Kimi K2.6 Moonshot AIopen | 45.1 | $0.23 |
| M2.7 MiniMaxopen | 38.9 | $0.10 |
| gpt-oss-20b OpenAIopen | 15.2 | $0.01 |