Fireworks AI
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Serverless inference — embeddings | Usage-based, per input token · Prices vary by embedding model parameter count | On request |
| On-demand deployments | 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 | On request |
| Managed training | 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 | On request |
| Enterprise reserved instance | Contact sales · Reserved GPUs; multi-region deployments, custom optimizations, better performance, and BYOC compatibility | On request |
As fireworks.ai lists them, read 7 Oct 2026. The maker's own page has the final word.
Facts from Fireworks AI's own pages
- Access controls
- The enterprise platform supports role-based access controls for sharing models, data, and deployments. · fireworks.ai, 7 Oct 2026
- API compatibility
- The serverless inference API is described as compatible with OpenAI and Anthropic APIs. · fireworks.ai, 7 Oct 2026
- Deployments
- Deployment choices include serverless, on-demand, and reserved instances, with options to deploy in the cloud or a customer's VPC. · fireworks.ai, 7 Oct 2026
- Developer tools
- Fireworks offers a Build SDK and a developer toolkit for testing, building agents, and running evaluations. · fireworks.ai, 7 Oct 2026
- Enterprise use cases
- Listed use cases include code assistance, conversational AI, agentic systems, search, multimodal applications, and enterprise RAG. · fireworks.ai, 7 Oct 2026
- Founded
- 2022 · fireworks.ai, 28 Sept 2026
- Inference
- Serverless inference is billed per token and offers Standard, Priority, and Fast serving paths. · fireworks.ai, 7 Oct 2026
- Integrations
- Enterprise customers can purchase Fireworks through AWS and GCP marketplaces, and its enterprise access supports Google, OIDC, and SAML single sign-on. · fireworks.ai, 7 Oct 2026
- Notable price condition
- Region-restricted on-demand deployments are priced at a 1.5x premium. · fireworks.ai, 7 Oct 2026
- Pricing controls
- Serverless users can enable automatic credit reloading or set a monthly spend limit. · fireworks.ai, 7 Oct 2026
- Product
- Fireworks describes its cloud as infrastructure for training and serving open models and specialized models. · fireworks.ai, 7 Oct 2026
- Security and compliance
- Fireworks states that it is HIPAA, SOC2-type2, and GDPR compliant and offers data residency and no data retention. · fireworks.ai, 7 Oct 2026
- Support
- Non-enterprise product support and feedback are directed to the Fireworks Discord and documentation. · fireworks.ai, 7 Oct 2026
- Training
- The platform supports supervised fine-tuning, preference fine-tuning, and reinforcement training. · fireworks.ai, 7 Oct 2026
Where Fireworks AI stands on Freedom251
- Model Hosting#11 of 25
- Ai Development Tools#21 of 26
- Llm Developer Tools#24 of 26