Icon for Fireworks AI

Fireworks AI

The production AI platform built for developers.

Fireworks AI offers a portfolio of LLMs and image models for a range of applications, like natural language processing, coding, and image generation. Model examples include Mixtral MoE 8x7B Instruct for instruction following, FireFunction V1 for function calling, and Llama 2 70B Chat optimized for dialogue applications. They also provide models specifically tailored to language tasks in French, Chinese, and Japanese, as well as StarCoder models for programming languages and Stable Diffusion for image generation.

Pricing: Per token usage

Hosting Cloud + Self-hosted
Pricing Usage Based, $0.10/1M tokens
HQ 🇺🇸 United States
Founded 2022
License PROPRIETARY
Compliance SOC 2 · HIPAA · GDPR · SSO

Data and privacy

Checked 17 November 2026
Data processed
Cloud infrastructure in the United States, Japan, Singapore, Australia, the UK and several EU countries (AWS, Google Cloud, Oracle); the default region for serverless requests is not stated source
Sub-processors
View the list ↗
US parent company
Yes

Read from Fireworks AI's own legal pages. "Not public" means it is not on their site; some providers share it on request.

Screenshot of Fireworks AI webpage

Fireworks AI prices by model

Per 1M tokens, read off Fireworks AI's own pricing page on the date shown.

Model Input / 1M Cached / 1M Output / 1M Checked Notes
DeepSeek V4.1 Flash $0.30 $0.006 $1.20 14 Nov 2026 Standard tier
DeepSeek V4.1 Flash 1017 $0.30 $0.006 $1.20 17 Nov 2026 Standard tier. US variant $0.45 / $0.009 / $1.80.
GLM 5.3 $1.40 $0.26 $4.40 14 Nov 2026 Standard tier
GLM 5.3 Flash $0.15 $0.03 $0.50 14 Nov 2026 Standard tier
Kimi K3 $3.00 $0.30 $15.00 14 Nov 2026 Standard tier
Kimi K3.1 Pro $2.00 $0.20 $10.00 17 Nov 2026 Standard tier.
MiniMax M3 $0.30 $0.06 $1.20 14 Nov 2026 Standard tier

Work on Fireworks AI? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →