Fireworks AI → OpenObserve

Automatically capture token usage, latency, and model metadata for every Fireworks AI inference call in your Python application. Fireworks AI exposes an OpenAI-compatible API, so instrumentation uses the standard OpenAI instrumentor pointed at the Fireworks endpoint.

Prerequisites

Python 3.9+
An OpenObserve account (cloud or self-hosted)
Your OpenObserve organisation ID and Base64-encoded auth token
A Fireworks AI API key

Installation

pip install openobserve-telemetry-sdk openinference-instrumentation-openai openai python-dotenv

Configuration

Create a .env file in your project root:

# OpenObserve instance URL
# Default for self-hosted: http://localhost:5080
OPENOBSERVE_URL=https://api.openobserve.ai/

# Your OpenObserve organisation slug or ID
OPENOBSERVE_ORG=your_org_id

# Basic auth token — Base64-encoded "email:password"
OPENOBSERVE_AUTH_TOKEN=Basic <your_base64_token>

# Fireworks AI API key
FIREWORKS_API_KEY=your-fireworks-api-key

Instrumentation

Call OpenAIInstrumentor().instrument() before creating the OpenAI client. Point the client at the Fireworks AI base URL and pass your Fireworks API key.

from dotenv import load_dotenv
load_dotenv()

from openinference.instrumentation.openai import OpenAIInstrumentor
from openobserve import openobserve_init

OpenAIInstrumentor().instrument()
openobserve_init()

import os
from openai import OpenAI

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

response = client.chat.completions.create(
    model="accounts/fireworks/models/llama-v3p3-70b-instruct",
    messages=[{"role": "user", "content": "Explain distributed tracing in one sentence."}],
)
print(response.choices[0].message.content)

What Gets Captured

Attribute	Description
`llm_model_name`	Model name (e.g. `accounts/fireworks/models/llama-v3p3-70b-instruct`)
`llm_provider`	`fireworks`
`llm_system`	`openai` (the client library used)
`llm_token_count_prompt`	Tokens in the prompt
`llm_token_count_completion`	Tokens in the response
`llm_token_count_total`	Total tokens consumed
`llm_token_count_prompt_details_cache_read`	Prompt tokens served from cache
`openinference_span_kind`	`LLM`
`operation_name`	`ChatCompletion`
`duration`	End-to-end request latency
`span_status`	`OK` or error status

Viewing Traces

Log in to OpenObserve and navigate to Traces
Click any span to inspect token counts and request metadata
Filter by llm_model_name to compare latency across different Fireworks models

Fireworks AI trace in OpenObserve

Next Steps

With Fireworks AI instrumented, every inference call is recorded in OpenObserve. From here you can monitor latency across open-source model variants, track token consumption, and identify slow or failing requests.