Fireworks AI pricing

4 plans on the record

See today's prices

Every plan

Enterprise reserved instance

Priced on request

Contact sales

Reserved GPUs; multi-region deployments, custom optimizations, better performance, and BYOC compatibility

Read 7 Oct 2026 · fireworks.ai

Managed training

Priced on request

Per 1M training tokens; rates vary by model size and training method

LoRA SFT, LoRA DPO, Full Param SFT, and Full Param DPO; rates range by model size

Read 7 Oct 2026 · fireworks.ai

On-demand deployments

Priced on request

Per GPU second, with listed per-minute and per-hour rates

H100 and H200: $0.134/minute or $8.00/hour; B200: $0.217/minute or $13.00/hour; B300: $0.250/minute or $15.00/hour; GB300: $0.334/minute or $20.00/hour

Read 7 Oct 2026 · fireworks.ai

Serverless inference — embeddings

Priced on request

Usage-based, per input token

Prices vary by embedding model parameter count

Read 7 Oct 2026 · fireworks.ai