How to beginner · 3 min read

Fireworks AI model not available fix

Quick answer

Use the correct Fireworks AI model name prefix accounts/fireworks/models/ when specifying the model parameter in your API call. Ensure your base_url is set to https://api.fireworks.ai/inference/v1 and your API key is loaded from os.environ to avoid model not found errors.

PREREQUISITES

Python 3.8+
Fireworks AI API key
pip install openai>=1.0

Setup

Install the openai Python package version 1.0 or higher. Set your Fireworks AI API key in the environment variable FIREWORKS_API_KEY. Use the OpenAI SDK with the Fireworks base URL to access Fireworks AI models.

bash

pip install openai>=1.0

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl (xx kB)
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

Use the OpenAI SDK with the Fireworks AI base URL and specify the full model name including the accounts/fireworks/models/ prefix. This example sends a chat completion request and prints the assistant's reply.

python

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/llama-v3p3-70b-instruct",
    messages=[{"role": "user", "content": "Hello, Fireworks AI!"}]
)

print(response.choices[0].message.content)

output

Hello, Fireworks AI! How can I assist you today?

Common variations

You can switch to other Fireworks AI models by changing the model parameter but always keep the accounts/fireworks/models/ prefix. For async usage, use asyncio with the OpenAI client. Streaming is supported via stream=True in chat.completions.create.

python

import os
import asyncio
from openai import OpenAI

async def main():
    client = OpenAI(
        api_key=os.environ["FIREWORKS_API_KEY"],
        base_url="https://api.fireworks.ai/inference/v1"
    )

    stream = await client.chat.completions.create(
        model="accounts/fireworks/models/llama-v3p3-70b-instruct",
        messages=[{"role": "user", "content": "Stream a response."}],
        stream=True
    )

    async for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

asyncio.run(main())

output

Streaming response text from Fireworks AI model...

Troubleshooting

If you get a model not found error, verify you are using the full model name with the accounts/fireworks/models/ prefix.
Ensure your FIREWORKS_API_KEY environment variable is set correctly.
Check your base_url is https://api.fireworks.ai/inference/v1.
For permission errors, confirm your API key has access to the requested model.

✅

Key Takeaways

Always use the full Fireworks AI model name starting with accounts/fireworks/models/.
Set base_url to https://api.fireworks.ai/inference/v1 when using OpenAI SDK.
Load your API key from the FIREWORKS_API_KEY environment variable.
Use streaming and async features with the OpenAI SDK for Fireworks AI.
Check model name and API key permissions if you encounter model not found errors.

Verified 2026-04 · accounts/fireworks/models/llama-v3p3-70b-instruct

Verify ↗