- Providers
- Fireworks
Fireworks: API pricing, speed & models
Fireworks hosts 12 active AI models, with input pricing from $0.22 per 1M tokens, with median throughput of 176 characters/sec, and P95 time to first token of 2.69s, with 100% success rate over 7 days. Compare Fireworks's API speed, pricing, and reliability against other inference providers.
Median throughput176 c/s
Median TTFT573ms
P95 TTFT2.69s
Success rate (7d)100%
From$0.22 /M tok
Catalog
Moonshot AI10MiniMax5DeepSeek4Fireworks AI4Alibaba Cloud / Qwen Team4Zhipu AI1
Type
Price
28 models| Model |
|---|
Kimi K3.1 Procache pricing |
Kimi K3.1 Procache pricing |
Kimi K3cache pricing |
Kimi K3cache pricing |