Fireworks AI
fireworks.ai
- Web
- API
- Self-hosted
6.3 Club score Visit fireworks.ai
Plans
Every plan and priceEnterprise reserved instance
—
Managed training
—
On-demand deployments
—
Serverless inference — embeddings
—
What the maker publishes
- Access controls
- The enterprise platform supports role-based access controls for sharing models, data, and deployments. source
- API compatibility
- The serverless inference API is described as compatible with OpenAI and Anthropic APIs. source
- Deployments
- Deployment choices include serverless, on-demand, and reserved instances, with options to deploy in the cloud or a customer's VPC. source
- Developer tools
- Fireworks offers a Build SDK and a developer toolkit for testing, building agents, and running evaluations. source
- Enterprise use cases
- Listed use cases include code assistance, conversational AI, agentic systems, search, multimodal applications, and enterprise RAG. source
- Founded
- 2022 source
- Inference
- Serverless inference is billed per token and offers Standard, Priority, and Fast serving paths. source
- Integrations
- Enterprise customers can purchase Fireworks through AWS and GCP marketplaces, and its enterprise access supports Google, OIDC, and SAML single sign-on. source
- Notable price condition
- Region-restricted on-demand deployments are priced at a 1.5x premium. source
- Pricing controls
- Serverless users can enable automatic credit reloading or set a monthly spend limit. source
- Product
- Fireworks describes its cloud as infrastructure for training and serving open models and specialized models. source
- Security and compliance
- Fireworks states that it is HIPAA, SOC2-type2, and GDPR compliant and offers data residency and no data retention. source
- Support
- Non-enterprise product support and feedback are directed to the Fireworks Discord and documentation. source
- Training
- The platform supports supervised fine-tuning, preference fine-tuning, and reinforcement training. source
Checked against the maker's pages on 7 Oct 2026.