OrcaRouter

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

OrcaRouter is an OpenAI-compatible AI gateway that routes requests across 200+ models. Its orcarouter/auto virtual model selects an upstream provider per request; you can also target specific models using a <provider>/<model> identifier. Because OrcaRouter mirrors the OpenAI API schema, you instrument it with the openinference-instrumentation-openai package by pointing the client’s base_url at OrcaRouter’s endpoint.

Prerequisites

• Python 3.9+
• An Arize AX account (sign up)
• An ORCAROUTER_API_KEY from the OrcaRouter dashboard

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="orcarouter-tracing-example"
export ORCAROUTER_API_KEY="<your-orcarouter-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 OrcaRouter.")

Run OrcaRouter

# 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 OrcaRouter's OpenAI-compatible endpoint.
client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="orcarouter/auto",
    messages=[
        {
            "role": "user",
            "content": "Why is the ocean salty? Answer in two sentences.",
        },
    ],
)

print(response.choices[0].message.content)

orcarouter/auto selects an upstream provider per request. The span recorded in Arize AX will show the resolved upstream model name (e.g. deepseek-v4-flash-202505) rather than orcarouter/auto.

To test without a funded account, replace orcarouter/auto with a free model such as deepseek/deepseek-v4-flash-free.

Expected output

Arize AX tracing initialized for OrcaRouter.
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 orcarouter-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 upstream model OrcaRouter selected (e.g. deepseek-v4-flash), not the virtual orcarouter/auto identifier.
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.
• OrcaRouter 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 OrcaRouter. Use your OrcaRouter API key (from the OrcaRouter dashboard), not an OpenAI or other provider key.
• 403 insufficient_user_quota. orcarouter/auto routes to paid upstream models and requires a funded OrcaRouter wallet. Add credit in the OrcaRouter dashboard, or use a free model such as deepseek/deepseek-v4-flash-free to test without balance.
• Model not found. OrcaRouter’s primary virtual model is orcarouter/auto. You can also pass specific provider models in <provider>/<model> format (e.g. deepseek/deepseek-v4-flash-free, openai/gpt-4.1-mini). See the OrcaRouter documentation for available identifiers.

Resources

OrcaRouter Documentation

OpenInference OpenAI Instrumentor (used for OrcaRouter)

OrcaRouter on GitHub