Cohere

Cohere provides enterprise LLMs through its Python client. The CohereInstrumentor captures Cohere v2 chat requests, responses, tool calls, and token counts as OpenInference LLM spans in Arize AX. It records input and output messages, invocation parameters, tool schemas and calls, tool-result links, usage.tokens, and the cohere provider and system attributes. Streaming chat_stream calls are traced when their streams are consumed.

Prerequisites

Python 3.10+
An Arize AX account (sign up)
A CO_API_KEY from the Cohere dashboard
Cohere Python client version 5.13.0 or later

Launch Arize AX

Sign in to your Arize AX account.
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-cohere cohere

Configure credentials

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

Setup tracing

# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.cohere import CohereInstrumentor

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

CohereInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for Cohere.")

Import instrumentation before constructing a Cohere client.

Run Cohere

# example.py
from instrumentation import tracer_provider

import cohere

client = cohere.ClientV2()
response = client.chat(
    model="command-a-03-2025",
    messages=[
        {
            "role": "user",
            "content": "Why is the ocean salty? Answer in two sentences.",
        },
    ],
)

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

Expected output

Arize AX tracing initialized for Cohere.
The ocean is salty because rivers dissolve minerals from rocks and carry them to the sea. Evaporation removes water while the dissolved salts remain and accumulate.

Verify in Arize AX

Open your Arize AX space and select project cohere-tracing-example.
You should see a new trace within ~30 seconds with a ClientV2.chat LLM span.
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)
AX CLI
SDK

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.

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.

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

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 AX. Run CohereInstrumentor().instrument(...) before constructing the client.
Authentication failed. Check that CO_API_KEY is set to an active Cohere API key.
No span for an endpoint. Only v2 ClientV2 and AsyncClientV2 chat and chat_stream calls are traced. The v1 cohere.Client client, embed, rerank, and classify endpoints are not traced.

OpenTelemetry

LLM Providers

Agent Frameworks

Coding Agents

Platforms

Orchestration

Evaluation

Prerequisites

Launch Arize AX

Install

Configure credentials

Setup tracing

Run Cohere

Expected output

Verify in Arize AX

Check from the skill, CLI, or SDK

Troubleshooting

Resources

OpenInference Cohere Instrumentor

Cohere Python client

​Prerequisites

​Launch Arize AX

​Install

​Configure credentials

​Setup tracing

​Run Cohere

​Expected output

​Verify in Arize AX

​Check from the skill, CLI, or SDK

​Troubleshooting

​Resources

OpenInference Cohere Instrumentor

Cohere Python client

Prerequisites

Launch Arize AX

Install

Configure credentials

Setup tracing

Run Cohere

Expected output

Verify in Arize AX

Check from the skill, CLI, or SDK

Troubleshooting

Resources