Fireworks AI
Inference host · 11 models · 15 priced routes · fireworks.ai
Models on Fireworks AI
| Model | In / out per 1M | Vs headline |
|---|---|---|
| GLM 5.3 Flash Fireworks AI | $0.15 / $0.5+245% vs headline | +245% |
| DeepSeek V4.1 Flash Fireworks AI | $0.22 / $0.66+26% vs headline | +26% |
| DeepSeek V4 Flash Vision Exp Fireworks AI | $0.22 / $0.66+2% vs headline | +2% |
| DeepSeek V4 Flash 0731 Fireworks AI | $0.22 / $0.66+317% vs headline | +317% |
| Muse Glimmer 30B Fireworks AI | $0.35 / $1.5+27% vs headline | +27% |
| Kimi K2.7 Code Fireworks AI | $0.95 / $4+33% vs headline | +33% |
| Kimi K2.6 Fireworks AI | $0.95 / $4+67% vs headline | +67% |
| DeepSeek V4 Pro 0813 Fireworks AI | $1.32 / $3.96+100% vs headline | +100% |
| GLM 5.3 Fireworks AI | $1.4 / $4.4+105% vs headline | +105% |
| GLM 5.2 Fireworks AI | $1.4 / $4.4+147% vs headline | +147% |
| GLM 5.2 Fireworks AI, fast-us | $2.1 / $6.6+270% vs headline | +270% |
| GLM 5.2 Fireworks AI, fast | $2.1 / $6.6+270% vs headline | +270% |
| Kimi K3 Fireworks AI | $3 / $15+61% vs headline | +61% |
| Kimi K3 Fireworks AI, us | $3.3 / $16.5+77% vs headline | +77% |
| Kimi K3 Fireworks AI, fast | $4.5 / $22.5+141% vs headline | +141% |
About Fireworks AI
Fireworks AI is an American artificial intelligence infrastructure company headquartered in San Mateo, California.
Batch: Process large volumes of requests asynchronously at 50% off Serverless per-token prices (docs.fireworks.ai batch-inference)
Caching: Batch jobs automatically use prompt caching for additional 50% cost savings on cached tokens
Across fru.devCompany profileSeries D, $1.5B (2026-07)
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.