Doubleword

Trace Doubleword inference API calls with OpenInference and send spans to Arize AX for LLM observability.

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. Arize AX captures every Doubleword call via the openinference-instrumentation-openai package — the same instrumentor that covers OpenAI’s hosted API.

Prerequisites

• Python 3.9+
• An Arize AX account (sign up)
• A DOUBLEWORD_API_KEY from the API Keys dashboard at app.doubleword.ai

Launch Arize

1. Sign in to your Arize AX account.
2. From Space Settings, copy your Space ID and API Key. You will set them as ARIZE_SPACE_ID and ARIZE_API_KEY below.

Install

pip install arize-otel openinference-instrumentation-openai openai

Configure credentials

export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="doubleword-tracing-example"
export DOUBLEWORD_API_KEY="<your-doubleword-api-key>"

Setup tracing

# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.openai import OpenAIInstrumentor

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for Doubleword.")

Run Doubleword

# example.py

# Importing instrumentation first ensures tracing is set up
# before `openai` is imported.
from instrumentation import tracer_provider

import os

from openai import OpenAI

# Point the OpenAI client at Doubleword's OpenAI-compatible endpoint.
client = 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)

Expected output

Arize AX tracing initialized for Doubleword.
The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.

Verify in Arize

1. Open your Arize AX space and select project doubleword-tracing-example.
2. You should see a new trace within ~30 seconds containing a ChatCompletion LLM span with the prompt, response, and token usage attached. The model name on the span will be the Doubleword model identifier you used (e.g. deepseek-ai/DeepSeek-V4-Flash).
3. If no traces appear, see Troubleshooting.

Check from the skill, CLI, or SDK

Confirm spans are actually reaching your Arize AX project. Use whichever fits your workflow — the skill and CLI work for any framework; the SDK check is shown for each language.

Arize skill (agent)

Install the Arize Skills plugin and let your coding agent check for you:

npx skills add Arize-ai/arize-skills

Then prompt your agent:

Use the arize-trace skill to export and analyze recent traces from my project. Confirm spans are arriving, and summarize any errors or latency issues.

AX CLI

Export recent spans for your project — any rows mean traces are landing:

ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
  --limit 5 --stdout | jq 'length'

A non-zero count confirms spans reached Arize AX. Run ax auth login first if you have not authenticated. See the ax spans reference.

SDK

Query the project’s spans and check that at least one came back.

Python

import os
from arize import ArizeClient

client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
resp = client.spans.list(
    project=os.environ["ARIZE_PROJECT_NAME"],
    space=os.environ["ARIZE_SPACE_ID"],
    limit=5,
)
count = len(resp.spans)
print(
    f"{count} span(s) found" if count else "No spans yet — recheck setup"
)

// Reads ARIZE_API_KEY from the environment.
import { listSpans } from "@arizeai/ax-client";

const { data: spans } = await listSpans({
  project: process.env.ARIZE_PROJECT_NAME!,
  space: process.env.ARIZE_SPACE_ID!,
  limit: 5,
});
const count = spans.length;
console.log(
  count ? `${count} span(s) found` : "No spans yet — recheck setup",
);

client, err := arize.NewClient(
    arize.Config{APIKey: os.Getenv("ARIZE_API_KEY")},
)
if err != nil {
    log.Fatal(err)
}
resp, err := client.Spans.List(ctx, spans.ListRequest{
    Project: os.Getenv("ARIZE_PROJECT_NAME"),
    Space:   os.Getenv("ARIZE_SPACE_ID"),
    Limit:   5,
})
if err != nil {
    log.Fatal(err)
}
fmt.Printf("%d span(s) found\n", len(resp.Spans))

SDK span references: Python · TypeScript · Go.

Troubleshooting

• No traces in Arize. Confirm ARIZE_SPACE_ID and ARIZE_API_KEY are set in the same shell that runs example.py. Enable OpenTelemetry debug logs with export OTEL_LOG_LEVEL=debug and re-run.
• Doubleword spans missing but other spans present. OpenAIInstrumentor().instrument(...) must run before any import openai. Make sure instrumentation.py is the first import in your entry point.
• 401 from Doubleword. Use your Doubleword API key (from the Doubleword dashboard), not your OpenAI key. They are different services with different credentials.
• 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.

Resources

Doubleword Documentation

OpenInference OpenAI Instrumentor (used for Doubleword)

Doubleword Platform