Fireworks AI Releases Firefunction-v2: An Open Weights Function Calling Model with Function Calling Capability on Par with GPT4o at 2.5x the Speed and 10% of the Cost
How does Firefunction-v2 integrate with multi-turn conversations?
Firefunction-v2 integrates with multi-turn conversations by retaining Llama 3's multi-turn instruction capability. It significantly outperforms Llama 3 in function-calling tasks, scoring 0.81 on a medley of public benchmarks compared to GPT-4o's 0.80. Firefunction-v2 costs $0.9 per output token, compared to GPT-4o's $15, and operates at 180 tokens per second versus GPT-4o's 69 tokens per second, providing a robust and efficient solution for multi-turn conversations.
What is the primary function of Firefunction-v2?
Firefunction-v2 is an open-source function-calling model designed to excel in real-world applications4. It integrates with multi-turn conversations, instruction following, and parallel function calling4. Firefunction-v2 offers a robust and efficient solution that rivals high-end models like GPT-4o but at a fraction of the cost and with superior speed and functionality4.
What makes Firefunction-v2 more cost-effective than GPT-4o?
Firefunction-v2 is more cost-effective than GPT-4o because it achieves speeds of 180 tokens/sec and has a pricing of $0.9 per 1M tokens, compared to GPT-4o's 69 tokens/sec and $15 per 1M output tokens2. This significant difference in speed and pricing makes Firefunction-v2 a more cost-efficient option for users.