Doubleword Tracing

Doubleword is a high-throughput, low-cost LLM inference platform serving open models such as Qwen and DeepSeek across realtime, async, and batch tiers. The endpoint at https://api.doubleword.ai/v1 mirrors OpenAI’s schema, so any OpenAI client works with base_url set to Doubleword. Phoenix captures every Doubleword call through the openinference-instrumentation-openai package, the same instrumentor that covers OpenAI’s hosted API.

Install

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

Setup

Add your Doubleword API key from the API Keys dashboard at app.doubleword.ai, along with your Phoenix connection details, as environment variables:

export DOUBLEWORD_API_KEY="<your-doubleword-api-key>"
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 Doubleword

import os
import openai

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

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Flash",
    messages=[
        {
            "role": "user",
            "content": "Why is the ocean salty? Answer in two sentences.",
        },
    ],
)
print(response.choices[0].message.content)

Observe

Now that you have tracing set up, all invocations of the OpenAI client pointed at Doubleword 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
Doubleword 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 Doubleword: Use your Doubleword API key from the Doubleword dashboard, not your OpenAI key
Model not found: Use a model identifier from the Doubleword model catalog (e.g. deepseek-ai/DeepSeek-V4-Flash). Identifiers are case-sensitive and include the publisher prefix
Base URL: Ensure you’re using https://api.doubleword.ai/v1 as the base URL

Developer Tools

LLM Providers

TypeScript

Python

Java

.NET

Platform

Vector Databases

Sandboxes

Evaluation Integrations

Coding Agents

Doubleword Tracing

Install

Setup

Run Doubleword

Observe

Common Issues

Resources

Doubleword Documentation

OpenInference OpenAI Instrumentation

​Install

​Setup

​Run Doubleword

​Observe

​Common Issues

​Resources

Doubleword Documentation

OpenInference OpenAI Instrumentation

Install

Setup

Run Doubleword

Observe

Common Issues

Resources