fireworks.ai Open in urlscan Pro
76.76.21.21  Public Scan

Form analysis
0 forms found in the DOM

Text Content

ModelsDocsPricing
Company
Login / Sign up

ModelsDocsPricingBlogCareersContactLogin / Sign up


THE PRODUCTION
AI PLATFORM BUILT FOR DEVELOPERS

Fireworks partners with the world's leading generative AI researchers to serve
the best models, at the fastest speeds.

Get Started for FreeContact Sales

Companies of all sizes trust Fireworks to power their production AI use-cases




MODELS CURATED AND OPTIMIZED BY FIREWORKS

Chat LLM

Mixtral MoE 8x7B Instruct

Mistral MoE 8x7B Instruct v0.1 model with Sparse Mixture of Experts. Fine tuned
for instruction following

Try now
Chat LLM

FireFunction V1

Fireworks' open-source function calling model.

Try now
Chat LLM

Llama 2 70B Chat

A fine-tuned version of Llama 2 70B, optimized for dialogue applications using
Reinforcement Learning from Human Feedback (RLHF), and perform comparably to
ChatGPT according to human evaluations.

Try now
Chat LLM

Mistral 7B Instruct

The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned
version of the Mistral-7B-v0.1 generative text model using a variety of publicly
available conversation datasets.

Try now
See all 89 models



THE FASTEST AND MOST UNCOMPROMISING AI PLATFORM!

0
Fireworks AI
tokens / second


0
Next provider
tokens / second


0
average provider
tokens / second

Industry Leading Performance

Independently benchmarked to have the top speed of all inference providers

1 Sec Cutoff2 Sec Cutoff3 Sec Cutoff0 req/sec20 req/sec40 req/sec60 req/sec80
req/sec

vLLM Quant

vLLM FP16

Fireworks FP16

Fireworks FP8



Enterprise Scale Throughput

Our proprietary stack blows open source options out of the water (see blog)

FireLLaVA: the first commercially permissive OSS LLaVA model

State-of-the-art Models

Use powerful models curated by Fireworks or our in-house trained multi-modal and
function-calling models

0 Billion+
tokens served in a day

Battle Tested for Reliability

Fireworks is the 2nd most used open-source model provider and also generates
over 1M images/day



TSPython
fetch("https://api.fireworks.ai/inference/v1/chat/completions", { method:
"POST", headers: { "Content-Type": "application "Authorization: "Bearer <API
KEY>", }, body: JSON.stringify({ model: "accounts/fireworks/mixtral-8x7b",
prompt: "Say this is a test", max_tokens: 700, }), })

Built for Developers

Our OpenAI-compatible API makes it easy to start building with Fireworks!



> "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, Poe by Quora

> "Fireworks is a go-to platform for deploying OSS models. Not only do they have
> superb tech - fast inference and low costs - but their team also offers
> incredible support on all things related to inference, finetuning, and OSS
> LLMs in general. LangChain users find great value for the ease of setting it
> up, the speed at which they add new models, and the ability to easily use the
> latest and greatest OSS models without breaking the bank"

Harrison Chase
CEO & Co-Founder, LangChain

> "Fireworks has been a fantastic partner as we build AI dev tools at
> Sourcegraph. Model inference runs super fast and reliably, which allows us to
> focus on core differentiators like finetuning, AI-powered code search, and
> deep code context that have made Cody the best AI coding assistant for
> completions and codebase-aware chat. They are also super responsive with
> feedback and ship at an amazing pace."

Beyang Liu
CTO, SourceGraph

> "Fireworks enabled us to deliver industry-leading speed for both LLM and image
> generation inference. It makes a huge difference for the customer experience
> when the AI responses are fast and interactive."

Ves Stoyanov
Head of AI, Tome

> "Fireworks has been marvelous, both in terms of features and support.
> Fireworks allows Artera's AI engineers to operate easily running both
> interactive and large scale batch jobs with a few clicks."

Nathan Silberman
Head of AI, Artera

> "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, Poe by Quora

> "Fireworks is a go-to platform for deploying OSS models. Not only do they have
> superb tech - fast inference and low costs - but their team also offers
> incredible support on all things related to inference, finetuning, and OSS
> LLMs in general. LangChain users find great value for the ease of setting it
> up, the speed at which they add new models, and the ability to easily use the
> latest and greatest OSS models without breaking the bank"

Harrison Chase
CEO & Co-Founder, LangChain

> "Fireworks has been a fantastic partner as we build AI dev tools at
> Sourcegraph. Model inference runs super fast and reliably, which allows us to
> focus on core differentiators like finetuning, AI-powered code search, and
> deep code context that have made Cody the best AI coding assistant for
> completions and codebase-aware chat. They are also super responsive with
> feedback and ship at an amazing pace."

Beyang Liu
CTO, SourceGraph

> "Fireworks enabled us to deliver industry-leading speed for both LLM and image
> generation inference. It makes a huge difference for the customer experience
> when the AI responses are fast and interactive."

Ves Stoyanov
Head of AI, Tome

> "Fireworks has been marvelous, both in terms of features and support.
> Fireworks allows Artera's AI engineers to operate easily running both
> interactive and large scale batch jobs with a few clicks."

Nathan Silberman
Head of AI, Artera


LEVEL UP WITH FIREWORKS AI ENTERPRISE

Get dedicated deployments for your models to ensure uptime and speed

Fireworks is proudly compliant with HIPAA and SOC2 and offers secure VPC and VPN
connectivity

Meet your needs with data privacy - own your data and your models

© 2024 Fireworks AI All rights reserved.


Toggle theme
Dark Modem

Pages

HomePricingModelsDocs

Company

BlogCareers

Legal

Terms of ServicePrivacy Policy
0 req/sec