Fireworks AI
The facts below are what the maker publishes about Fireworks AI, checked and dated. Our editors have not written about it yet.
Plans and prices
From Fireworks AI's own pricing page, checked 7 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Enterprise reserved instance | Priced on request | Reserved GPUs; multi-region deployments, custom optimizations, better performance, and BYOC compatibility · Contact sales |
| Managed training | — | LoRA SFT, LoRA DPO, Full Param SFT, and Full Param DPO; rates range by model size · Per 1M training tokens; rates vary by model size and training method |
| On-demand deployments | — | 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 · Per GPU second, with listed per-minute and per-hour rates |
| Serverless inference — embeddings | — | Prices vary by embedding model parameter count · Usage-based, per input token |
The facts
Each one read from Fireworks AI's own pages, with the date it was checked.
What it does
- Access controls
- The enterprise platform supports role-based access controls for sharing models, data, and deployments.checked 7 Oct 2026
- API compatibility
- The serverless inference API is described as compatible with OpenAI and Anthropic APIs.checked 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.checked 7 Oct 2026
- Developer tools
- Fireworks offers a Build SDK and a developer toolkit for testing, building agents, and running evaluations.checked 7 Oct 2026
- Enterprise use cases
- Listed use cases include code assistance, conversational AI, agentic systems, search, multimodal applications, and enterprise RAG.checked 7 Oct 2026
- Inference
- Serverless inference is billed per token and offers Standard, Priority, and Fast serving paths.checked 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.checked 7 Oct 2026
- Pricing controls
- Serverless users can enable automatic credit reloading or set a monthly spend limit.checked 7 Oct 2026
- Product
- Fireworks describes its cloud as infrastructure for training and serving open models and specialized models.checked 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.checked 7 Oct 2026
- Support
- Non-enterprise product support and feedback are directed to the Fireworks Discord and documentation.checked 7 Oct 2026
- Training
- The platform supports supervised fine-tuning, preference fine-tuning, and reinforcement training.checked 7 Oct 2026
The company
- Founded
- 2022checked 28 Sep 2026
Money
- Notable price condition
- Region-restricted on-demand deployments are priced at a 1.5x premium.checked 7 Oct 2026
Alternatives to Fireworks AI
- 1
Cloudflare Stream
AndroidiOSWebAPI6.9 - 2
Runpod Serverless
Free planWebAPILinuxmacOS6.6Free plan - 3
Replicate
Free planWebAPI6.3Free plan - 4
Baseten
Free planWebAPISelf-hosted6.1Free plan - 5
BentoML
Free planWebAPILinuxSelf-hosted6.1Free plan - 6
6.0From $0.06 a month