Cohere

​

Setup

pnpm add braintrust cohere-ai

npm install braintrust cohere-ai

BRAINTRUST_API_KEY=<your-braintrust-api-key>
COHERE_API_KEY=<your-cohere-api-key>

# For organizations on the EU data plane, use https://api-eu.braintrust.dev
# For self-hosted deployments, use your data plane URL
# BRAINTRUST_API_URL=<your-braintrust-api-url>

​

Auto-instrumentation

import { initLogger } from "braintrust";
import { CohereClientV2 } from "cohere-ai";

initLogger({
  projectName: "cohere-example",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const client = new CohereClientV2({
  token: process.env.COHERE_API_KEY,
});

const response = await client.chat({
  model: "command-a-03-2025",
  messages: [
    {
      role: "user",
      content: "Explain tracing in one sentence.",
    },
  ],
  maxTokens: 64,
  temperature: 0,
});

console.log(response.message?.content);

node --import braintrust/hook.mjs trace-cohere-auto.js

​

Manual instrumentation

import { initLogger, wrapCohere } from "braintrust";
import { CohereClientV2 } from "cohere-ai";

initLogger({
  projectName: "cohere-example",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const client = wrapCohere(
  new CohereClientV2({
    token: process.env.COHERE_API_KEY,
  }),
);

const response = await client.chat({
  model: "command-a-03-2025",
  messages: [
    {
      role: "user",
      content: "Explain tracing in one sentence.",
    },
  ],
  maxTokens: 64,
  temperature: 0,
});

console.log(response.message?.content);

​

What Braintrust traces

• Chat completion spans (cohere.chat and cohere.chatStream), with messages and request parameters as input; chat output (including aggregated tool calls for streaming) and token usage; first-token timing for streaming.
• Extended thinking content for reasoning models, captured from streaming cohere.chatStream responses as structured thinking content blocks in the span output.
• Embedding spans (cohere.embed), with input texts and request parameters; output summarized as the first embedding’s vector length.
• Rerank spans (cohere.rerank), with query and documents as input; results as a list of {index, relevance_score} items.
• Token usage metrics (prompt, completion, total, plus cached prompt tokens and reasoning tokens when reported).
• Request metadata (model and selected request parameters) and response metadata (response ID, finish reason, generation ID, response type, and Cohere API version when present).
• Errors captured on every call.

​

Resources

• Cohere TypeScript SDK
• Cohere API reference