Last updated: 2026-04-20

Fireworks AI Integration

Route Fireworks AI API calls through SpendLil.

SpendLil proxies Fireworks AI's API. Swap api.fireworks.ai for fireworks.gateway.spendlil.ai and add X-SpendLil-Key. Fireworks is OpenAI-compatible — use the OpenAI SDK with the Fireworks gateway.

URL Pattern

diff Before → After 
- POST https://api.fireworks.ai/inference/v1/chat/completions
+ POST https://fireworks.gateway.spendlil.ai/inference/v1/chat/completions

OpenAI SDK (Python)

python Use the OpenAI SDK with the Fireworks gateway 
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ['FIREWORKS_API_KEY'],
    base_url='https://fireworks.gateway.spendlil.ai/inference/v1',
    default_headers={'X-SpendLil-Key': os.environ['SPENDLIL_KEY']},
)

response = client.chat.completions.create(
    model='accounts/fireworks/models/llama-v3p3-70b-instruct',
    messages=[{'role': 'user', 'content': 'Hello'}],
)
print(response.choices[0].message.content)

cURL

bash Direct HTTP request 
curl https://fireworks.gateway.spendlil.ai/inference/v1/chat/completions \
  -H "Authorization: Bearer $FIREWORKS_API_KEY" \
  -H "X-SpendLil-Key: $SPENDLIL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "accounts/fireworks/models/llama-v3p3-70b-instruct",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
ℹ OpenAI-compatible

Fireworks' chat completions API mirrors OpenAI's schema. Any OpenAI SDK or tool that accepts a base_url override will work unchanged.