> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentium.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Cohere

> Use Cohere Command models with Agentium — RAG-optimized, tool calling, and fine-tuning support.

# Cohere

Use Cohere's **Command** models for RAG, tool calling, and enterprise workloads. Cohere excels at retrieval-augmented generation and offers fine-tuning support.

<Info>
  Agentium tries the native `cohere-ai` SDK first; if not installed, it falls back to the `openai` SDK via Cohere's [OpenAI-compatible endpoint](https://docs.cohere.com/docs/openai-compatibility).
</Info>

***

## Setup

<Tabs>
  <Tab title="Install (Option A — Native)">
    ```bash theme={null}
    npm install cohere-ai
    ```
  </Tab>

  <Tab title="Install (Option B — OpenAI compat)">
    ```bash theme={null}
    npm install openai
    ```
  </Tab>

  <Tab title="Environment">
    Get your API key from [dashboard.cohere.com](https://dashboard.cohere.com/api-keys):

    ```bash theme={null}
    export CO_API_KEY="..."
    ```
  </Tab>
</Tabs>

***

## Factory

```typescript theme={null}
import { cohere } from "@agentium/core";

const model = cohere("command-r-plus");
```

<ParamField path="modelId" type="string" required>
  Model ID (e.g., `"command-r-plus"`, `"command-r"`, `"command-r7b-12-2024"`, `"command-light"`).
</ParamField>

<ParamField path="config" type="CohereConfig" required={false}>
  Optional `{ apiKey? }`.
</ParamField>

***

## Supported Models

| Model                 | Description                      | Best For                           |
| --------------------- | -------------------------------- | ---------------------------------- |
| `command-r-plus`      | Flagship model, strong reasoning | RAG, complex tasks, tool calling   |
| `command-r`           | Fast and capable                 | General tasks, moderate complexity |
| `command-r7b-12-2024` | Small but strong                 | RAG, reasoning on a budget         |
| `command`             | General purpose                  | Basic tasks                        |
| `command-light`       | Fastest, smallest                | Simple tasks, high throughput      |

***

## Basic Example

```typescript theme={null}
import { Agent, cohere } from "@agentium/core";

const agent = new Agent({
  name: "cohere-agent",
  model: cohere("command-r-plus"),
  instructions: "You are a helpful assistant.",
});

const result = await agent.run("Summarize the key benefits of microservices architecture.");
console.log(result.text);
```

***

## RAG-Optimized Usage

Cohere's Command R models are specifically designed for retrieval-augmented generation:

```typescript theme={null}
import { Agent, cohere, defineTool } from "@agentium/core";
import { z } from "zod";

const agent = new Agent({
  name: "rag-agent",
  model: cohere("command-r-plus"),
  instructions:
    "You are a knowledge-grounded assistant. Always use the search tool to find " +
    "relevant information before answering. Cite your sources.",
  tools: [
    defineTool({
      name: "searchDocs",
      description: "Search internal documentation",
      parameters: z.object({ query: z.string() }),
      execute: async ({ query }) =>
        JSON.stringify([
          { title: "Deployment Guide", content: `Guide for: ${query}...`, source: "docs/deploy.md" },
          { title: "API Reference", content: `API info for: ${query}...`, source: "docs/api.md" },
        ]),
    }),
  ],
  maxToolRoundtrips: 3,
});

const result = await agent.run("How do I deploy our service to production?");
console.log(result.text);
```

***

## Tool Calling

```typescript theme={null}
import { Agent, cohere, defineTool } from "@agentium/core";
import { z } from "zod";

const agent = new Agent({
  name: "tool-agent",
  model: cohere("command-r-plus"),
  tools: [
    defineTool({
      name: "createTicket",
      description: "Create a support ticket",
      parameters: z.object({
        title: z.string(),
        priority: z.enum(["low", "medium", "high"]),
        description: z.string(),
      }),
      execute: async ({ title, priority }) => `Ticket created: "${title}" [${priority}] — ID: TK-1234`,
    }),
  ],
});

const result = await agent.run("Create a high-priority ticket: 'API returning 500 errors on /users endpoint'");
console.log(result.text);
```

***

## Full Example

```typescript theme={null}
import { Agent, cohere, CostTracker, defineTool } from "@agentium/core";
import { z } from "zod";

const costTracker = new CostTracker({
  pricing: {
    "command-r-plus": { promptPer1k: 0.0025, completionPer1k: 0.01 },
    "command-r": { promptPer1k: 0.00015, completionPer1k: 0.0006 },
  },
});

const agent = new Agent({
  name: "enterprise-agent",
  model: cohere("command-r-plus"),
  instructions: "You are an enterprise assistant with document search capabilities.",
  tools: [
    defineTool({
      name: "search",
      description: "Search knowledge base",
      parameters: z.object({ query: z.string() }),
      execute: async ({ query }) => `Found 5 results for "${query}"`,
    }),
  ],
  costTracker,
  maxToolRoundtrips: 5,
});

const result = await agent.run("What is our company's vacation policy?");
console.log(result.text);
console.log(`Cost: $${costTracker.getSummary().totalCost.toFixed(4)}`);
```

***

## Environment Variables

| Variable     | Description    |
| ------------ | -------------- |
| `CO_API_KEY` | Cohere API key |

***

## Cross-References

* [Azure AI Foundry](/models/azure-foundry) — Cohere models on Azure
* [AWS Bedrock](/models/aws-bedrock) — Cohere models on AWS
* [Tools](/agents/tools) — Tool calling guide
* [Knowledge Base](/knowledge/overview) — RAG with vector search