Using Firefunction V2 on Fireworks AI
Implementation guide · Firefunction · Fireworks AI
Fireworks AI exposes Firefunction V2 through model ID accounts/fireworks/models/firefunction-v2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-09-30. Next refresh: weekly.
Quick Start
- 1
- 2Use the Fireworks AI SDK or REST API to call
accounts/fireworks/models/firefunction-v2— see the documentation for request format. - 3
Code Examples
pip install openaiFIREWORKS_API_KEYaccounts/fireworks/models/firefunction-v2Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="accounts/fireworks/models/firefunction-v2",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Fireworks AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.90 |
| Output tokens | $0.90 |
Capabilities
No model capability flags are currently sourced.
About Firefunction V2
Firefunction-v2, developed by Fireworks AI, is an open-source function-calling large language model built on the Llama 3-70b base model. It excels in conversational and instruction-following tasks, with enhanced capabilities for function calling. Notably, it supports parallel function calling, handling up to 30 function specifications, and smoothly integrates chat with function execution. It rivals GPT-4o in function-calling performance while being more cost-effective and offering quicker responses. Its 8k context window and OpenAI-compatible API make it easily integratable into diverse applications 123.