LLM ReferenceLLM Reference

Firefunction

Fireworks AILlama 3 Community
2 models2024Up to 32K ctxFrom $0.5/1M input

About

The Firefunction family of large language models is specifically designed for efficient function calling, enabling seamless interaction with external APIs and access to real-time data. The initial version, Firefunction v1, was built on the Mixtral 8x7B model and achieved GPT-4-level accuracy in practical scenarios, with the advantages of faster speeds and open-source accessibility. Its successor, Firefunction v2, utilizes the Llama 3 model to enhance its function-calling capabilities while maintaining robust conversational and instruction-following features. This version excels in multi-turn dialogues, parallel function calling, and consistently surpasses Llama 3 in function-calling tasks, delivering results akin to GPT-4o on public benchmarks. These models are tailored for real-world use, combining accuracy, speed, and cost effectiveness.

Specifications(2 models)

Firefunction model specifications comparison
ModelReleasedContextParameters
Firefunction V12024-018K46B
Firefunction V22024-0132K70B

Available From(1 provider)

Fireworks AI

Pricing

Firefunction model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Firefunction V1Fireworks AI$0.5$0.5Provisioned

Frequently Asked Questions

What is Firefunction?
The Firefunction family of large language models is specifically designed for efficient function calling, enabling seamless interaction with external APIs and access to real-time data. The initial version, Firefunction v1, was built on the Mixtral 8x7B model and achieved GPT-4-level accuracy in practical scenarios, with the advantages of faster speeds and open-source accessibility. Its successor, Firefunction v2, utilizes the Llama 3 model to enhance its function-calling capabilities while maintaining robust conversational and instruction-following features. This version excels in multi-turn dialogues, parallel function calling, and consistently surpasses Llama 3 in function-calling tasks, delivering results akin to GPT-4o on public benchmarks. These models are tailored for real-world use, combining accuracy, speed, and cost effectiveness.
How many models are in the Firefunction family?
The Firefunction family contains 2 models.
What is the latest Firefunction model?
The latest model is Firefunction V1, released in 2024-01.
How much does Firefunction cost?
Firefunction models are available at $0.5/1M input tokens through providers like Fireworks AI.

Models(2)

Firefunction V1

2024-018K46B1 provider

Firefunction V2

2024-0132K70B1 provider