For agents › Models › Command

Command + live news

Built for retrieval-augmented generation, with citations as a first-class output rather than something you prompt for. A natural fit for news grounding.

Vendor	Cohere, Canada
Base URL	`https://api.cohere.com/v2`
Model id	`command-a-03-2025`
Model credential	`COHERE_API_KEY`
Tool format	Cohere v2 — OpenAI-shaped tool calling with citations as a first-class output.
News API key	none required
Vendor docs	https://docs.cohere.com/docs/tool-use

Base URLs and model ids change often, and several vendors run separate mainland and international endpoints with non-interchangeable keys. Check the vendor docs above before copying. The part that does not change is the tool itself — our API has no key, no version negotiation and no SDK.

Working example

python

import json, requests, cohere

co = cohere.ClientV2()         # COHERE_API_KEY

TOOLS = [{
    "type": "function",
    "function": {
        "name": "search_news",
        "description": ("Search worldwide news published in the last 30 days. "
                        "Free, keyless. Use 2-5 keywords, not a question."),
        "parameters": {
            "type": "object",
            "properties": {
                "q":    {"type": "string"},
                "date": {"type": "string"},
                "lang": {"type": "string"},
                "size": {"type": "integer"},
            },
            "required": ["q"],
        },
    },
}]

IDENT = {"agent_name": "news-agent", "software": "command",
         "model": "command-a-03-2025"}

msgs = [{"role": "user", "content": "What happened with grain exports this week?"}]
r = co.chat(model="command-a-03-2025", messages=msgs, tools=TOOLS)

if r.message.tool_calls:
    msgs.append(r.message)
    for tc in r.message.tool_calls:
        data = requests.get("https://freenewsapi.ai/v1/search",
                            params={**json.loads(tc.function.arguments), **IDENT},
                            timeout=20).json()
        msgs.append({"role": "tool", "tool_call_id": tc.id,
                     "content": json.dumps(data)[:60000]})
    r = co.chat(model="command-a-03-2025", messages=msgs, tools=TOOLS)

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

Worth knowing about Command

The v2 API is OpenAI-shaped; v1 was not. Do not mix documentation.
Its documents mode can take retrieved articles directly and return span-level citations — often better than tool calling for this job.

Test the tool without the model

Before debugging a tool-calling loop, confirm the data side works. It needs no credentials, so this runs anywhere:

bash

curl "https://freenewsapi.ai/v1/search?q=grain+exports&date=7d&size=5"

If that returns results and your loop still fails, the problem is in the model's tool handling, not in the data.

Prompt it properly

The single most common failure is the model phrasing the query as a sentence. Search is AND across every term, so q=what happened with grain exports matches nothing. Put this in the system prompt:

system prompt

Use search_news for anything about current events or recent developments.
Phrase the query as 2-5 keywords that would appear in a headline, never as a question.
Good: "grain export prices". Bad: "what is happening with grain exports".
Scan titles first. Only request full_text for articles you will actually cite.
If a search returns nothing, drop the least essential keyword and try once more.
No results means no coverage in this corpus \u2014 not that the event did not happen.

Same format

Command uses the cohere tool-calling shape. These take the same code with a different base URL and model name: none in this list.

← All models · Identify your agent · Token costs