Fireworks AI Tracing

Fireworks AI provides fast model inference through an OpenAI-compatible API. Set the OpenAI client’s base_url to Fireworks and Phoenix captures each completion through openinference-instrumentation-openai.

This page uses Fireworks’ OpenAI-compatible API. There is no separate Fireworks-specific OpenInference instrumentor required.

Install

pip install arize-phoenix-otel openinference-instrumentation-openai openai

Setup

Add your Fireworks AI API key and the model you want to call, along with your Phoenix connection details, as environment variables:

export FIREWORKS_API_KEY="<your-fireworks-api-key>"
export FIREWORKS_MODEL="<your-fireworks-model-id>"
export PHOENIX_COLLECTOR_ENDPOINT="<your-phoenix-collector-endpoint>"  # use http://localhost:6006 for local Phoenix
export PHOENIX_API_KEY="<your-phoenix-api-key>"  # required for Phoenix Cloud or authenticated Phoenix

Connect your application to Phoenix with the register function:

Run Fireworks AI

import os
import openai

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

response = client.chat.completions.create(
    model=os.environ["FIREWORKS_MODEL"],
    messages=[
        {
            "role": "user",
            "content": "Name two signals an LLM trace should capture.",
        },
    ],
)
print(response.choices[0].message.content)

Observe

Now that you have tracing set up, all invocations of the OpenAI client pointed at Fireworks AI will be streamed to your running Phoenix for observability and evaluation. Each request appears as a ChatCompletion LLM span with the prompt, response, model name, token usage, and latency.

Common Issues

No traces in Phoenix: Confirm PHOENIX_COLLECTOR_ENDPOINT (and PHOENIX_API_KEY if your Phoenix requires one) is set in the same shell that runs your app
Fireworks AI spans missing: Call register() before you create the OpenAI client, and make sure openinference-instrumentation-openai is installed so auto_instrument=True picks it up
401 from Fireworks: Use your Fireworks API key, not your OpenAI key
Model not found: Confirm FIREWORKS_MODEL matches a model identifier from the Fireworks model catalog
Base URL: Ensure you’re using https://api.fireworks.ai/inference/v1 as the base URL

Developer Tools

LLM Providers

TypeScript

Python

Java

.NET

Platform

Vector Databases

Sandboxes

Evaluation Integrations

Coding Agents

Fireworks AI Tracing

Install

Setup

Run Fireworks AI

Observe

Common Issues

Resources

Fireworks OpenAI Compatibility

OpenInference OpenAI Instrumentation

​Install

​Setup

​Run Fireworks AI

​Observe

​Common Issues

​Resources

Fireworks OpenAI Compatibility

OpenInference OpenAI Instrumentation

Install

Setup

Run Fireworks AI

Observe

Common Issues

Resources