Fireworks AI

:::info We support ALL Fireworks AI models, just set fireworks_ai/ as a prefix when sending completion requests :::

Overview

This guide explains how to integrate LiteLLM with Fireworks AI. You can connect to Fireworks AI in three main ways:

1. <b> Using Fireworks AI serverless models </b> – Easy connection to Fireworks-managed models.
2. <b> Connecting to a model in your own Fireworks account </b> – Access models that are hosted within your Fireworks account.
3. <b> Connecting via a direct-route deployment </b> – A more flexible, customizable connection to a specific Fireworks instance.

API Key

# env variable
os.environ['FIREWORKS_AI_API_KEY']

Sample Usage - Serverless Models

from litellm import completion

os.environ['FIREWORKS_AI_API_KEY'] = ""
response = completion(
    model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
)
print(response)

Sample Usage - Serverless Models - Streaming

from litellm import completion

os.environ['FIREWORKS_AI_API_KEY'] = ""
response = completion(
    model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
    stream=True
)

for chunk in response:
    print(chunk)

Sample Usage - Models in Your Own Fireworks Account

from litellm import completion

os.environ['FIREWORKS_AI_API_KEY'] = ""
response = completion(
    model="fireworks_ai/accounts/fireworks/models/YOUR_MODEL_ID", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
)
print(response)

Sample Usage - Direct-Route Deployment

from litellm import completion

os.environ['FIREWORKS_AI_API_KEY'] = "YOUR_DIRECT_API_KEY"
response = completion(
    model="fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b#accounts/gitlab/deployments/2fb7764c", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
   api_base="https://gitlab-2fb7764c.direct.fireworks.ai/v1"
)
print(response)

Note: The above is for the chat interface, if you want to use the text completion interface it's model="text-completion-openai/accounts/fireworks/models/qwen2p5-coder-7b#accounts/gitlab/deployments/2fb7764c"

Usage with LiteLLM Proxy

1. Set Fireworks AI Models on config.yaml

model_list:
  - model_name: fireworks-llama-v3-70b-instruct
    litellm_params:
      model: fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
      api_key: "os.environ/FIREWORKS_AI_API_KEY"

2. Start Proxy

litellm --config config.yaml

3. Test it

curl --location 'http://0.0.0.0:4000/chat/completions' \\
--header 'Content-Type: application/json' \\
--data ' {
      "model": "fireworks-llama-v3-70b-instruct",
      "messages": [
        {
          "role": "user",
          "content": "what llm are you"
        }
      ]
    }
'

client = openai.OpenAI(
    api_key="anything",
    base_url="http://0.0.0.0:4000"
)

# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="fireworks-llama-v3-70b-instruct", messages = [
    {
        "role": "user",
        "content": "this is a test request, write a short poem"
    }
])

print(response)

from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
    ChatPromptTemplate,
    HumanMessagePromptTemplate,
    SystemMessagePromptTemplate,
)
from langchain.schema import HumanMessage, SystemMessage

chat = ChatOpenAI(
    openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
    model = "fireworks-llama-v3-70b-instruct",
    temperature=0.1
)

messages = [
    SystemMessage(
        content="You are a helpful assistant that im using to make a test request to."
    ),
    HumanMessage(
        content="test from litellm. tell me why it's amazing in 1 sentence"
    ),
]
response = chat(messages)

print(response)

Document Inlining

LiteLLM supports document inlining for Fireworks AI models. This is useful for models that are not vision models, but still need to parse documents/images/etc.

LiteLLM will add #transform=inline to the url of the image_url, if the model is not a vision model.See Code

from litellm import completion

os.environ["FIREWORKS_AI_API_KEY"] = "YOUR_API_KEY"
os.environ["FIREWORKS_AI_API_BASE"] = "https://audio-prod.api.fireworks.ai/v1"

completion = litellm.completion(
    model="fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://storage.googleapis.com/fireworks-public/test/sample_resume.pdf"
                    },
                },
                {
                    "type": "text",
                    "text": "What are the candidate's BA and MBA GPAs?",
                },
            ],
        }
    ],
)
print(completion)

1. Setup config.yaml

model_list:
  - model_name: llama-v3p3-70b-instruct
    litellm_params:
      model: fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct
      api_key: os.environ/FIREWORKS_AI_API_KEY
    #   api_base: os.environ/FIREWORKS_AI_API_BASE [OPTIONAL], defaults to "https://api.fireworks.ai/inference/v1"

2. Start Proxy

litellm --config config.yaml

3. Test it

curl -L -X POST 'http://0.0.0.0:4000/chat/completions' \\
-H 'Content-Type: application/json' \\
-H 'Authorization: Bearer YOUR_API_KEY' \\
-d '{"model": "llama-v3p3-70b-instruct", 
    "messages": [        
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://storage.googleapis.com/fireworks-public/test/sample_resume.pdf"
                    },
                },
                {
                    "type": "text",
                    "text": "What are the candidate's BA and MBA GPAs?",
                },
            ],
        }
    ]}'

Disable Auto-add

If you want to disable the auto-add of #transform=inline to the url of the image_url, you can set the auto_add_transform_inline to False in the FireworksAIConfig class.

litellm.disable_add_transform_inline_image_block = True

litellm_settings:
    disable_add_transform_inline_image_block: true

Reasoning Effort

The reasoning_effort parameter is supported on select Fireworks AI models. Supported models include:

from litellm import completion

os.environ["FIREWORKS_AI_API_KEY"] = "YOUR_API_KEY"

response = completion(
    model="fireworks_ai/accounts/fireworks/models/qwen3-8b",
    messages=[
        {"role": "user", "content": "What is the capital of France?"}
    ],
    reasoning_effort="low",
)
print(response)

curl http://0.0.0.0:4000/v1/chat/completions \\
  -H "Content-Type: application/json" \\
  -H "Authorization: Bearer $LITELLM_KEY" \\
  -d '{
    "model": "fireworks_ai/accounts/fireworks/models/qwen3-8b",
    "messages": [
      {
        "role": "user",
        "content": "What is the capital of France?"
      }
    ],
    "reasoning_effort": "low"
  }'

Supported Models - ALL Fireworks AI Models Supported!

:::info We support ALL Fireworks AI models, just set fireworks_ai/ as a prefix when sending completion requests :::

Supported Embedding Models

:::info We support ALL Fireworks AI models, just set fireworks_ai/ as a prefix when sending embedding requests :::

Audio Transcription

Quick Start

from litellm import transcription

os.environ["FIREWORKS_AI_API_KEY"] = "YOUR_API_KEY"
os.environ["FIREWORKS_AI_API_BASE"] = "https://audio-prod.api.fireworks.ai/v1"

response = transcription(
    model="fireworks_ai/whisper-v3",
    audio=audio_file,
)

Pass API Key/API Base in .transcription

1. Setup config.yaml

model_list:
  - model_name: whisper-v3
    litellm_params:
      model: fireworks_ai/whisper-v3
      api_base: https://audio-prod.api.fireworks.ai/v1
      api_key: os.environ/FIREWORKS_API_KEY
    model_info:
      mode: audio_transcription

2. Start Proxy

litellm --config config.yaml

3. Test it

curl -L -X POST 'http://0.0.0.0:4000/v1/audio/transcriptions' \\
-H 'Authorization: Bearer sk-1234' \\
-F 'file=@"/Users/krrishdholakia/Downloads/gettysburg.wav"' \\
-F 'model="whisper-v3"' \\
-F 'response_format="verbose_json"' \\

Rerank

Quick Start

from litellm import rerank

os.environ["FIREWORKS_AI_API_KEY"] = "YOUR_API_KEY"

query = "What is the capital of France?"
documents = [
    "Paris is the capital and largest city of France, home to the Eiffel Tower and the Louvre Museum.",
    "France is a country in Western Europe known for its wine, cuisine, and rich history.",
    "The weather in Europe varies significantly between northern and southern regions.",
    "Python is a popular programming language used for web development and data science.",
]

response = rerank(
    model="fireworks_ai/fireworks/qwen3-reranker-8b",
    query=query,
    documents=documents,
    top_n=3,
    return_documents=True,
)
print(response)

Pass API Key/API Base in .rerank

1. Setup config.yaml

model_list:
  - model_name: qwen3-reranker-8b
    litellm_params:
      model: fireworks_ai/fireworks/qwen3-reranker-8b
      api_key: os.environ/FIREWORKS_API_KEY
    model_info:
      mode: rerank

2. Start Proxy

litellm --config config.yaml

3. Test it

curl http://0.0.0.0:4000/rerank \\
  -H "Authorization: Bearer sk-1234" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "qwen3-reranker-8b",
    "query": "What is the capital of France?",
    "documents": [
        "Paris is the capital and largest city of France, home to the Eiffel Tower and the Louvre Museum.",
        "France is a country in Western Europe known for its wine, cuisine, and rich history.",
        "The weather in Europe varies significantly between northern and southern regions.",
        "Python is a popular programming language used for web development and data science."
    ],
    "top_n": 3,
    "return_documents": true
  }'

Supported Models