Using Firefunction V1 on Fireworks AI
Implementation guide · Firefunction · Fireworks AI
Fireworks AI exposes Firefunction V1 through model ID accounts/fireworks/models/firefunction-v1. 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-v1— see the documentation for request format. - 3
Code Examples
pip install openaiFIREWORKS_API_KEYaccounts/fireworks/models/firefunction-v1Fireworks 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-v1",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Fireworks AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.50 |
| Output tokens | $0.50 |
Capabilities
No model capability flags are currently sourced.
About Firefunction V1
FireFunction V1 is a cutting-edge function-calling large language model developed by Fireworks AI. It is tailored for real-world applications that demand structured information generation and decision-making through routing. The model boasts near GPT-4 level quality in handling such tasks and processes data approximately four times faster than GPT-4 when operated on the Fireworks platform. A standout feature is its "any" parameter in tool_choice, ensuring a persistent selection of functions. Additionally, it offers seamless integration due to API compatibility with OpenAI's function-calling API, allowing smooth incorporation into existing systems.