Fireworks AI Integration

Connect Helicone with Fireworks AI, a platform that provides a fast, affordable, and customizable solution for generative artificial intelligence that helps product developers run, fine-tune, and share large language models.

You can follow their documentation here: https://docs.fireworks.ai/getting-started/quickstart

Gateway Integration

1. Create a Helicone account

   Log into helicone or create an account. Once you have an account, you can generate an API key.

2. Create an FireworksAI account

   Log into www.fireworks.ai or create an account. Once you have an account, you can generate an API key.

3. Set HELICONE_API_KEY and FIREWORKS_API_KEY as environment variable

   HELICONE_API_KEY=<your API key>
   FIREWORKS_API_KEY=<your API key>
   

4. Modify the base URL and add Auth headers

   Replace the following FireworksAI URL with the Helicone Gateway URL:

   https://api.fireworks.ai/inference/v1/chat/completions -> https://fireworks.helicone.ai/inference/v1/chat/completions

   and then add the following authentication headers.

   Helicone-Auth: `Bearer ${HELICONE_API_KEY}`
   Authorization: `Bearer ${FIREWORKS_API_KEY}`
   

Now you can access all the models on FireworksAI with a simple fetch call:

Example

curl --request POST \
  --url https://fireworks.helicone.ai/inference/v1/completions \
  --header "Authorization: Bearer $FIREWORKS_API_KEY" \
  --header "Helicone-Auth: Bearer $HELICONE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "accounts/fireworks/models/llama-v3-8b-instruct",
    "prompt": "Say this is a test"
}'

For more information on how to use headers, see Helicone Headers docs. And for more information on how to use FireworksAI, see FireworksAI Docs.