Join Our Community
Get the earliest access to hand-picked content weekly for free.
Spam-free guaranteed! Only insights.
Join Our Community
Get the earliest access to hand-picked content weekly for free.
Spam-free guaranteed! Only insights.
Build with top AI models like Chat LLAMA & Mistral. Fireworks AI offers a production platform for developers with optimized solutions and industry-leading performance.
126.7K
Similarweb
Pricing Model
Pricing Plans
FLUX.1 Kontext Pro
Image Generation flat rate
$ 0.04
per image
FLUX.1 Kontext Max
Image Generation flat rate
$ 0.08
per image
Text and Vision Models < 4B parameters
Serverless Inference for models with less than 4 billion parameters
$ 0.1
per 1 million tokens
Text and Vision Models 4B - 16B parameters
Serverless Inference for models between 4 billion and 16 billion parameters
$ 0.2
per 1 million tokens
Text and Vision Models > 16B parameters
Serverless Inference for models exceeding 16 billion parameters
$ 0.9
per 1 million tokens
MoE Models 0B - 56B parameters
Serverless Inference for Mixture of Experts models (e.g., Mixtral 8x7B)
$ 0.5
per 1 million tokens
MoE Models 56.1B - 176B parameters
Serverless Inference for Mixture of Experts models (e.g., DBRX, Mixtral 8x22B)
$ 1.2
per 1 million tokens
DeepSeek V3 family
$0.56 per 1 million input tokens; $1.68 per 1 million output tokens
$ 0.56
per 1 million tokens
DeepSeek R1 0528
$1.35 per 1 million input tokens; $5.40 per 1 million output tokens
$ 1.35
per 1 million tokens
GLM-4.5, GLM-4.6
$0.55 per 1 million input tokens; $2.19 per 1 million output tokens
$ 0.55
per 1 million tokens
Meta Llama 3.1 405B
Serverless Inference for Meta Llama 3.1 405B model
$ 3
per 1 million tokens
Meta Llama 4 Maverick (Basic)
$0.22 per 1 million input tokens; $0.88 per 1 million output tokens
$ 0.22
per 1 million tokens
Meta Llama 4 Scout (Basic)
$0.15 per 1 million input tokens; $0.60 per 1 million output tokens
$ 0.15
per 1 million tokens
Qwen3 235B Family, GLM-4.5 Air
$0.22 per 1 million input tokens; $0.88 per 1 million output tokens
$ 0.22
per 1 million tokens
Qwen3 30B, Qwen Coder Flash
$0.15 per 1 million input tokens; $0.60 per 1 million output tokens
$ 0.15
per 1 million tokens
Kimi K2 Instruct, Kimi K2 Thinking
$0.60 per 1 million input tokens; $2.50 per 1 million output tokens
$ 0.6
per 1 million tokens
Qwen3 Coder 480B
$0.45 per 1 million input tokens; $1.80 per 1 million output tokens
$ 0.45
per 1 million tokens
OpenAI gpt-oss-120b
$0.15 per 1 million input tokens; $0.60 per 1 million output tokens
$ 0.15
per 1 million tokens
OpenAI gpt-oss-20b
$0.07 per 1 million input tokens; $0.30 per 1 million output tokens
$ 0.07
per 1 million tokens
Whisper-v3-large
Speech-to-Text service, billed per second
$ 0
per audio minute
Whisper-v3-large-turbo
Speech-to-Text service, billed per second
$ 0
per audio minute
Streaming ASR v1
Speech-to-Text service, billed per second
$ 0
per audio minute
Streaming ASR v2
Speech-to-Text service, billed per second
$ 0
per audio minute
Non-Flux Models (e.g., SDXL, Playground)
Image Generation, approximately $0.0039 per 30-step image
$ 0
per step
FLUX.1 [dev]
Image Generation, approximately $0.014 per 28-step image
$ 0
per step
FLUX.1 [schnell]
Image Generation, approximately $0.0014 per 4-step image
$ 0
per step
A100 80 GB GPU
On-Demand Deployments and Reinforcement Fine-Tuning, billed per second
$ 2.9
per hour
H100 80 GB GPU
On-Demand Deployments and Reinforcement Fine-Tuning, billed per second
$ 4
per hour
H200 141 GB GPU
On-Demand Deployments and Reinforcement Fine-Tuning, billed per second
$ 6
per hour
B200 180 GB GPU
On-Demand Deployments and Reinforcement Fine-Tuning, billed per second
$ 9
per hour
Hosting Fine-Tuned Models
Free deploying and hosting up to 100 fine-tuned models; charged per-token usage when utilized
$ 0
---
Discover alternative AI tools similar to Fireworks.Ai that may better suit your needs.
AI Photo Enhancer & Art Generator: Unleash Your Creativity with Luminar Neo
Generative AI Tools Directory: Discover Telegram Messenger – A Powerful Communication Platform
AI Logo Generator: Create Professional Logos with Fiverr's AI Design Templates and Generative AI Technology
Explore professional roles that benefit from using Fireworks.Ai.
Use AI to simplify your game development from 3D rendering to character building, story development, debugging, and even AR!
4918 Tools
Unlock top AI tools for everyday workflows for Graphic Designer. See pros, cons & pricing; to streamline your work. Pick the best tool today.
4317 Tools
Create beautiful 3D renders in minutes with AI tools for 3D design, characters, animation, and VR.
2644 Tools
AI resources for 3D imaging and textiles, closet creations, photo fine-tuning, avatars, and makeup creation and editing.
2967 Tools
Design stunning spaces with AI tools for 3D modeling, interior layouts, augmented reality, and automated design for creative and functional interiors.
2834 Tools
uses AI for 3D printing and rendering, rendering for interiors, architectural renderings for meetings, layouts of homes, visualization.
2429 Tools
Use AI for 3D modeling, generative and animated designs, branding, and blockchain capabilities.
4306 Tools
