Fireworks RFT now available! Fine-tune open models that outperform frontier models. Try today

Build. Tune. Scale.

Open-source AI models at blazing speed, optimized for your use case, scaled globally with the Fireworks Inference Cloud

Get started Talk to our team

Fireworks AI Cloud

What Can You Build on Fireworks

From experimentation to production, Fireworks provides the platform to build your Generative AI capabilities - optimized and at scale

Code Assistance \
\
IDE copilots, code generation, debugging agents

Learn more

Conversational AI \
\
Customer support bots, internal helpdesk assistants, multilingual chat

Learn more

Agentic Systems \
\
Multi-step reasoning, planning, and execution pipelines

Learn more

Search \
\
Enterprise assistants, summarization, semantic search, personalized recommendations

Learn more

Multimedia \
\
Text, vision, and speech in real-time workflows

Learn more

Enterprise RAG \
\
Secure, scalable retrieval for knowledge bases and documents

Learn more

Model library

Run the latest open models with a single line of code

Fireworks gives you instant access to the most popular OSS models — optimized for cost, speed, and quality on the fastest AI cloud

View all models

\
\
Chronos Hermes 13B v2\
\
$0.2/M Tokens • 4096 Context\
\
LLM

\
\
Gemma 3 27B Instruct\
\
$0.9/M Tokens • 131072 Context\
\
LLM

\
\
Qwen3 Coder 480B A35B Instruct\
\
$0.45/M Input • $1.8/M Output • 262144 Context\
\
LLM

\
\
GLM-4.6\
\
$0.55/M Input • $2.19/M Output • 202752 Context\
\
LLM

\
\
OpenAI gpt-oss-20b\
\
$0.07/M Input • $0.3/M Output • 131072 Context\
\
LLM

\
\
FLUX.1 Kontext Pro\
\
$0.04/Image\
\
Image

\
\
Kimi K2 Instruct\
\
$0.6/M Input • $2.5/M Output • 131072 Context\
\
LLM

\
\
Segmind Stable Diffusion 1B (SSD-1B)\
\
$0.00013/Step\
\
Image

\
\
Whisper V3 Large\
\
$0/M Tokens\
\
Audio

\
\
Nous Hermes Llama2 13B\
\
$0.2/M Tokens • 4096 Context\
\
LLM

\
\
GLM-4.5\
\
$0.55/M Input • $2.19/M Output • 131072 Context\
\
LLM

\
\
Deepseek R1 05/28\
\
$1.35/M Input • $5.4/M Output • 163840 Context\
\
LLM

\
\
Llama 3 8B Instruct (HF version)\
\
$0.2/M Tokens • 8192 Context\
\
LLM

\
\
Chronos Hermes 13B v2\
\
$0.2/M Tokens • 4096 Context\
\
LLM

\
\
Gemma 3 27B Instruct\
\
$0.9/M Tokens • 131072 Context\
\
LLM

\
\
Qwen3 Coder 480B A35B Instruct\
\
$0.45/M Input • $1.8/M Output • 262144 Context\
\
LLM

\
\
GLM-4.6\
\
$0.55/M Input • $2.19/M Output • 202752 Context\
\
LLM

Building with Fireworks

Run and tune your models on our highly scalable, optimized virtual cloud infrastructure

Globally distributed virtual cloud infrastructure running on the latest hardware

Enterprise-grade security and reliability across mission-critical workloads

Fast inference engine delivering industry-leading throughput and latency.

Optimized deployments across quality, speed,
and cost

Model Lifecycle Management

Complete AI model lifecycle management

Run the fastest inference, tune with ease, and scale globally, all without managing infrastructure

Build \
\
Go from idea to output in seconds—with just a prompt. Run the latest open models on Fireworks serverless, with no GPU setup or cold starts. Move to production with on-demand GPUs that auto-scale as you grow

Learn more

Tune \
\
Fine-tune to meet your use case without the complexity. Get the highest-quality results from any open model using advanced tuning techniques like reinforcement learning, quantization-aware tuning, and adaptive speculation

Learn more

Scale \
\
Scale production workloads seamlessly, anywhere, without managing infrastructure. Fireworks automatically provisions AI infrastructure across any deployment type, so you can focus on building

Learn more

Why Fireworks

Startup velocity. Enterprise-grade stability.

From AI Natives to Enterprises, Fireworks powers everything from rapid prototyping to mission-critical workloads

[AI Natives \
\

• Day 0 support for latest models\
• Highest quality and performance, lowest cost\
• Complete set of developer features no matter where you are on the journey](https://fireworks.ai/ai-native)

Learn More

[Enterprise \
\

• SOC2, HIPAA, and GDPR compliant\
• Bring your own cloud or run on ours\
• Zero data retention and complete data sovereignty](https://fireworks.ai/enterprise)

Learn More

Customer Love

What our customers are saying

"Fireworks has been a fantastic partner in building AI dev tools at Sourcegraph. Their fast, reliable model inference lets us focus on fine-tuning, AI-powered code search, and deep code context, making Cody the best AI coding assistant. They are responsive and ship at an amazing pace."

Beyang Liu | CTO at Sourcegraph

"By partnering with Fireworks to fine-tune models, we reduced latency from about 2 seconds to 350 milliseconds, significantly improving performance and enabling us to launch AI features at scale. That improvement is a game changer for delivering reliable, enterprise-scale AI"

Sarah Sachs | AI Lead at Notion

“Fireworks has been an amazing partner getting our Fast Apply and Copilot++ models running performantly. They exceeded other competitors we reviewed on performance. After testing their quantized model quality for our use cases, we have found minimal degradation. Fireworks helps implement task specific speed ups and new architectures, allowing us to achieve bleeding edge performance!”

Sualeh Asif | CPO at Cursor

"We've had a really great experience working with Fireworks to host open source models, including SDXL, Llama, and Mistral. After migrating one of our models, we noticed a 3x speedup in response time, which made our app feel much more responsive and boosted our engagement metrics."

Spencer Chan | Product Lead at Quora

"Fireworks has been a fantastic partner in building AI dev tools at Sourcegraph. Their fast, reliable model inference lets us focus on fine-tuning, AI-powered code search, and deep code context, making Cody the best AI coding assistant. They are responsive and ship at an amazing pace."

Beyang Liu | CTO at Sourcegraph

"By partnering with Fireworks to fine-tune models, we reduced latency from about 2 seconds to 350 milliseconds, significantly improving performance and enabling us to launch AI features at scale. That improvement is a game changer for delivering reliable, enterprise-scale AI"

Sarah Sachs | AI Lead at Notion

“Fireworks has been an amazing partner getting our Fast Apply and Copilot++ models running performantly. They exceeded other competitors we reviewed on performance. After testing their quantized model quality for our use cases, we have found minimal degradation. Fireworks helps implement task specific speed ups and new architectures, allowing us to achieve bleeding edge performance!”

Sualeh Asif | CPO at Cursor

"We've had a really great experience working with Fireworks to host open source models, including SDXL, Llama, and Mistral. After migrating one of our models, we noticed a 3x speedup in response time, which made our app feel much more responsive and boosted our engagement metrics."

Spencer Chan | Product Lead at Quora

Case Study

Sentient Achieved 50% Higher GPU Throughput with Sub-2s Latency

Sentient waitlisted 1.8M users in 24 hours, delivering sub-2s latency across 15-agent workflows with 50% higher throughput per GPU and zero infra sprawl, all powered by Fireworks

Read the Case Study

50%

Higher throughput per GPU

What’s new in our blog

\
\
Fireworks and AMD partner to power the next gen of AI infrastructure on AMD Instinct™ GPUs \
\
10/20/2025

\
\
LLM on the edge: Model picking with Fireworks Eval Protocol + Ollama \
\
10/15/2025

\
\
Announcing Embeddings and Reranking On Fireworks AI \
\
10/9/2025

Start building today

Instantly run popular and specialized models.

Get Started Talk to an expert