Inference Providers documentation
Fireworks AI
Fireworks AI
Fireworks AI is a developer-centric platform that delivers high-performance generative AI solutions, enabling efficient deployment and fine-tuning of large language models (LLMs) and image models.
Supported tasks
Chat Completion (LLM)
Find out more about Chat Completion (LLM) here.
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fireworks-ai",
api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx",
)
completion = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3-0324",
messages=[
{
"role": "user",
"content": "What is the capital of France?"
}
],
max_tokens=500,
)
print(completion.choices[0].message)Chat Completion (VLM)
Find out more about Chat Completion (VLM) here.
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fireworks-ai",
api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx",
)
completion = client.chat.completions.create(
model="meta-llama/Llama-4-Scout-17B-16E-Instruct",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
],
max_tokens=500,
)
print(completion.choices[0].message)