About Fireworks AI
Fireworks AI is a cloud platform for hosting open-source AI models optimized for specific use cases and scales globally via the Fireworks Inference Cloud. It serves developers and enterprises looking to build, tune, and scale generative AI applications from experimentation through production.
Key Features
For teams building and deploying generative AI, the platform pairs an OSS model library with a managed inference layer to shorten iteration cycles and control costs in real-world workloads:
OSS Model Library
Instant access to popular open-source models, optimized for cost, speed, and quality on the Fireworks Cloud.
One-Line Deployment
Run the latest open models with a single line of code, simplifying integration and iteration.
Global Inference Cloud
Scales globally to support production workloads with low latency and high throughput.
Use-case Ready Capabilities
Prebuilt templates for Code Assistance, Conversational AI, Agentic Systems, Search, Multimedia, and Enterprise RAG to accelerate development.
Summary
Best for AI/ML engineering teams, developer platforms, and enterprise product teams deploying production-scale generative AI.
Pricing
View pricingBase model (Less than 4B parameters)
$0.10 / per 1M tokens
Base model (4B - 16B parameters)
$0.20 / per 1M tokens
Base model (More than 16B parameters)
$0.90 / per 1M tokens
MoE model (0B - 56B parameters)
$0.50 / per 1M tokens
MoE model (56.1B - 176B parameters)
$1.20 / per 1M tokens
DeepSeek V3 family
$0.56 input, $1.68 output / per 1M tokens
DeepSeek R1 0528
$1.35 input, $5.4 output / per 1M tokens
GLM-4.5, GLM-4.6
$0.55 input, $2.19 output / per 1M tokens
Meta Llama 3.1 405B
$3.00 / per 1M tokens
Meta Llama 4 Maverick (Basic)
$0.22 input, $0.88 output / per 1M tokens
Meta Llama 4 Scout (Basic)
$0.15 input, $0.60 output / per 1M tokens
Qwen3 235B Family
$0.22 input, $0.88 output / per 1M tokens
Qwen3 30B, Qwen Coder Flash
$0.15 input, $0.60 output / per 1M tokens
Kimi K2 Instruct, Kimi K2 Thinking
$0.60 input, $2.50 output / per 1M tokens
Qwen3 Coder 480B
$0.45 input, $1.80 output / per 1M tokens
OpenAI gpt-oss-120b
$0.15 input, $0.60 output / per 1M tokens
OpenAI gpt-oss-20b
$0.07 input, $0.30 output / per 1M tokens
Whisper-v3-large
$0.0015 / per audio minute
Whisper-v3-large-turbo
$0.0009 / per audio minute
Streaming ASR v1
$0.0032 / per audio minute
Streaming ASR v2
$0.0035 / per audio minute
All Non-Flux Models
$0.0002 / per image
FLUX.1 [dev]
N/A / per image
FLUX.1 [schnell]
N/A / per image
FLUX.1 Kontext Pro
$0.04 / per image
FLUX.1 Kontext Max
$0.08 / per image
up to 150M
$0.008 / per 1M input tokens
150M - 350M
$0.016 / per 1M input tokens
Qwen3 8B
$0.1 / per 1M input tokens
Supervised Fine Tuning (Models up to 16B parameters)
$0.50 / per 1M training tokens
Supervised Fine Tuning (Models 16.1B - 80B)
$3.00 / per 1M training tokens
Supervised Fine Tuning (Models 80B - 300B)
$6.00 / per 1M training tokens
Supervised Fine Tuning (Models >300B)
$10.00 / per 1M training tokens
On-Demand - A100 80 GB GPU
$2.90 / per hour
On-Demand - H100 80 GB GPU
$4.00 / per hour
On-Demand - H200 141 GB GPU
$6.00 / per hour
On-Demand - B200 180 GB GPU
$9.00 / per hour
