LLM Reference
Fireworks AI Platform

Fireworks AI Platform

Fireworks AI

AIHighlight

Platform

The Fireworks AI Platform is a comprehensive generative AI solution that enables developers and businesses to build, customize, and deploy AI models at scale. It supports a diverse range of cutting-edge open-source models, including Meta's Llama and Stable Diffusion, for tasks such as natural language processing and image generation. The platform's serverless architecture allows for quick deployment without extensive infrastructure management, operating on a pay-as-you-go basis. Users can fine-tune models using parameter-efficient techniques, ensuring tailored AI solutions that maintain high performance for specific business needs. Optimized for high throughput and low latency, the platform can handle trillions of inferences daily while providing a seamless user experience. It offers tools for efficient model maintenance and iteration, allowing businesses to focus on innovation rather than complex AI model management. The platform's design facilitates easy integration and customization, enabling organizations to effectively scale their AI-powered solutions. With its cost-efficient approach and comprehensive features, the Fireworks AI Platform empowers businesses to leverage advanced AI capabilities for enhanced productivity and competitive advantage in their respective markets.

About Fireworks AI

Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment. Their platform is designed to optimize the development and serving of generative AI applications, enabling businesses to quickly build and scale AI-powered solutions. Fireworks.ai emphasizes minimizing the cost to serve while maximizing the potential of generative AI technologies, making advanced AI capabilities more accessible and practical for a wide range of applications.

Available Models(84)

ModelInput (per 1M)Output (per 1M)Type
Firefunction V2$0$0Serverless
Firefunction V1$0.50$0.50Provisioned
Mixtral 8x7B$0.5$0.5Serverless
Mixtral 8x22B v0.1$1.2$1.2ServerlessProvisioned
FireLLaVA 13B$0.9$0.9Serverless
Llama 3 70B Instruct$0.9$0.9Serverless
Llama 3 8B Instruct$0.2$0.2Serverless
Nous Capybara 7B V1.9$0.20$0.20Provisioned
Gemma 7B Instruct$0.20$0.20Provisioned
Hermes 2 Pro Mistral 7B$0.20$0.20Provisioned
Llama Guard 2 8B$0.20$0.20Provisioned
Stable LM 2 Zephyr 1.6B$0.10$0.10Provisioned
Llama 2 7B Chat$0.20$0.20Provisioned
Yi Large$0.90$0.90Provisioned
Mistral 7B v0.1$0.20$0.20Provisioned
Nous Hermes 2 Mixtral 8x7B$0.50$0.50Provisioned
Phi-3 Mini 128K$0.10$0.10Provisioned
Phi-3 Vision$0.2$0.2Serverless
Qwen1.5-72B$0.90$0.90Provisioned
Qwen2 72B$0.9$0.9Serverless
Stable LM Zephyr 3B$0.10$0.10Provisioned
Stable Code 3B$0.10$0.10Provisioned
StarCoder2 15B$0.20$0.20Provisioned
StarCoder2 7B$0.2$0.2ServerlessProvisioned
Nous Capybara 34B$0.90$0.90Provisioned
Llama 3.1 405B Instruct$3$3Serverless
Llama 3.1 70B Instruct$0.9$0.9Serverless
Llama 3.1 8B Instruct$0.2$0.2Serverless
Chronos Hermes 13B V2$0.20$0.20Provisioned
CodeGemma 2B$0.10$0.10Provisioned
CodeLlama 13B$0.20$0.20Provisioned
CodeLlama 13B Python$0.20$0.20Provisioned
CodeLlama 34B$0.90$0.90Provisioned
CodeLlama 34B Python$0.90$0.90Provisioned
CodeLlama 70B$0.90$0.90Provisioned
CodeLlama 70B Python$0.90$0.90Provisioned
CodeLlama 7B$0.20$0.20Provisioned
CodeLlama 7B Python$0.20$0.20Provisioned
Dolphin 2.6 Mixtral 8x7B$0.50$0.50Provisioned
CodeQwen1.5 7B$0.20$0.20Provisioned
DeepSeek Coder 1.3B$0.10$0.10Provisioned
DeepSeek Coder 6.7B$0.20$0.20Provisioned
DeepSeek Coder 33B$0.90$0.90Provisioned
DeepSeek Coder 7B V1.5$0.20$0.20Provisioned
DeepSeek Coder V2$1.2$1.2ServerlessProvisioned
DeepSeek Coder V2 Lite$0.5$0.5ServerlessProvisioned
Dolphin 2.9.2 Qwen2 72B$0.90$0.90Provisioned
ELYZA Japanese Llama 2 7B$0.20$0.20Provisioned
Gemma 2 9B Instruct$0.2$0.2Serverless
Toppy M 7B$0.20$0.20Provisioned
Japanese StableLM Gamma 7B$0.20$0.20Provisioned
Japanese Stable VLM$0.20$0.20Provisioned
Llama Guard 7B$0.20$0.20Provisioned
LLaVA 1.6 Hermes Yi 34B$0.90$0.90Provisioned
MythoMax L2 13B$0.2$0.2Serverless
Japanese StableLM 70B$0.90$0.90Provisioned
Mistral 7B OpenOrca$0.20$0.20Provisioned
Nous Hermes 2 Yi 34B$0.90$0.90Provisioned
Nous Hermes Llama 2 13B$0.20$0.20Provisioned
Nous Hermes Llama 2 70B$0.90$0.90Provisioned
Nous Hermes Llama 2 7B$0.20$0.20Provisioned
OpenChat 3.5 (0106)$0.20$0.20Provisioned
OpenHermes 2 Mistral 7B$0.20$0.20Provisioned
OpenHermes 2.5 Mistral 7B$0.20$0.20Provisioned
Phi-2$0.10$0.10Provisioned
Phind CodeLlama 34B V2$0.90$0.90Provisioned
Phind CodeLlama 34B V1$0.90$0.90Provisioned
Phind CodeLlama 34B Python V1$0.90$0.90Provisioned
Pythia 12B$0.20$0.20Provisioned
Qwen-14B$0.20$0.20Provisioned
Qwen-72B$0.90$0.90Provisioned
Snorkel Mistral PairRM$0.20$0.20Provisioned
StarCoder2 3B$0.10$0.10Provisioned
Yi 34B$0.90$0.90Provisioned
Yi 6B$0.20$0.20Provisioned
Zephyr 7B Beta$0.20$0.20Provisioned
CodeGemma 7B Instruct$0.20$0.20Provisioned
StarCoder$0.2$0.2Serverless
DeepSeek V3$56$168Serverless
GLM-4.7$60$220Serverless
GLM-5$100$320Serverless
Kimi K2 Instruct$60$250Serverless
Kimi K2 Thinking$60$250Serverless
Kimi K2.5$60$300Serverless

Company Info

Founded2017
San Mateo, California, United States