Skip to content
SPECIFICTION
Get listed

Fireworks AI

fireworks.ai

WebAPISelf-hosted
Visit fireworks.ai
Spec score 7.2 #10 of 25 in Model Hosting

Spec sheet

Product
Fireworks describes its cloud as infrastructure for training and serving open models and specialized models.Read 7 Oct 2026 · fireworks.ai
Integrations
Enterprise customers can purchase Fireworks through AWS and GCP marketplaces, and its enterprise access supports Google, OIDC, and SAML single sign-on.Read 7 Oct 2026 · fireworks.ai
Support
Non-enterprise product support and feedback are directed to the Fireworks Discord and documentation.Read 7 Oct 2026 · fireworks.ai
Founded
2022Read 28 Sep 2026 · fireworks.ai
Access controls
The enterprise platform supports role-based access controls for sharing models, data, and deployments.Read 7 Oct 2026 · fireworks.ai
API compatibility
The serverless inference API is described as compatible with OpenAI and Anthropic APIs.Read 7 Oct 2026 · fireworks.ai
Deployments
Deployment choices include serverless, on-demand, and reserved instances, with options to deploy in the cloud or a customer's VPC.Read 7 Oct 2026 · fireworks.ai
Developer tools
Fireworks offers a Build SDK and a developer toolkit for testing, building agents, and running evaluations.Read 7 Oct 2026 · fireworks.ai
Enterprise use cases
Listed use cases include code assistance, conversational AI, agentic systems, search, multimodal applications, and enterprise RAG.Read 7 Oct 2026 · fireworks.ai
Inference
Serverless inference is billed per token and offers Standard, Priority, and Fast serving paths.Read 7 Oct 2026 · fireworks.ai
Notable price condition
Region-restricted on-demand deployments are priced at a 1.5x premium.Read 7 Oct 2026 · fireworks.ai
Pricing controls
Serverless users can enable automatic credit reloading or set a monthly spend limit.Read 7 Oct 2026 · fireworks.ai
Security and compliance
Fireworks states that it is HIPAA, SOC2-type2, and GDPR compliant and offers data residency and no data retention.Read 7 Oct 2026 · fireworks.ai
Training
The platform supports supervised fine-tuning, preference fine-tuning, and reinforcement training.Read 7 Oct 2026 · fireworks.ai

Plans and prices

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 Price not published 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 Price not published 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 Price not published Usage-based, per input token Prices vary by embedding model parameter count Read 7 Oct 2026 · fireworks.ai

Every Fireworks AI plan and price →

Where Specifiction places it

Alternatives to Fireworks AIAll alternatives →