Fireworks AI API pricing
9 models · USD per 1M tokens · verified 2026-10-23
Fireworks AI serves 9 of the models we track, 7 of them open-weights. The cheapest is GLM-5.3-FlashX at $0.15 input and $0.50 output per million tokens. For 5 of these models, Fireworks AI is the cheapest tracked host.
// models on Fireworks AI
| model | lab | in $/1M | out $/1M | ctx | vs best price |
|---|---|---|---|---|---|
| GLM-5.3-FlashX BEST | Z.AI (Zhipu) | $0.15 | $0.50 | 1M | −59.7% |
| MiniMax-M3.1-Flash BEST | MiniMax | $0.15 | $0.60 | 1M | best |
| GPT OSS 120B | OpenAI | $0.15 | $0.60 | 131.1K | +273.4% |
| DeepSeek V4.1 Flash | DeepSeek | $0.21 | $0.84 | 1.05M | +22.5% |
| MiniMax-M3 | MiniMax | $0.30 | $1.20 | 1M | best |
| GLM-5.3 BEST | Z.AI (Zhipu) | $0.98 | $3.08 | 1M | −30% |
| Muse Spark Open BEST | Meta | $1.25 | $4.25 | 1.05M | best |
| Qwen3.8 Max | Alibaba (Qwen) | $2.00 | $6.00 | 1M | best |
| Kimi K3 BEST | Moonshot AI | $2.10 | $10.50 | 1.05M | −30% |
// how to read this page
Prices are Fireworks AI's base-tier list prices per million tokens. "vs best price" compares Fireworks AI's blended price (3 × input + output) / 4 with the lowest price we track for the same model, whether it comes from the lab's own API or another host. Open each model for its full price history and every host that serves it.