Cohere

Trial key with no expiry. Strong at RAG, embeddings and rerank.

Cohere’s Command models are built for RAG: embeddings, rerank and long-document chat on one key. The trial key does not expire and needs no card, but it is licensed for prototypes, not production.

1,000 requests a month, 20 a minute, and Command A (command-a-03-2025) reaches 256K of context. Command A+ is command-a-plus-05-2026. The OpenAI-shaped path is /compatibility/v1; Cohere’s own API lives at /v2.

Free models: 12
Max context: 256K
Free tier: 1,000 requests per month
Requirement: Email account, no card

Endpoint

Base URLhttps://api.cohere.com/compatibility/v1

Env varCOHERE_API_KEY

Rate limit20 requests/minute, 1,000 requests/month

OpenAI-compatible
Native SDK: Cohere SDK
text
image

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.cohere.com/compatibility/v1',
  apiKey: process.env.COHERE_API_KEY
})

const response = await client.chat.completions.create({
  model: 'command-a-03-2025',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cohere.com/compatibility/v1",
    api_key=os.environ["COHERE_API_KEY"],
)

response = client.chat.completions.create(
    model="command-a-03-2025",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

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

curl https://api.cohere.com/compatibility/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COHERE_API_KEY" \
  -d '{
    "model": "command-a-03-2025",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

npm install cohere-ai

import { CohereClientV2 } from 'cohere-ai'

const cohere = new CohereClientV2({ token: process.env.COHERE_API_KEY })

const response = await cohere.chat({
  model: 'command-a-03-2025',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.message.content?.[0].text)

pip install cohere

import os
import cohere

client = cohere.ClientV2(api_key=os.environ["COHERE_API_KEY"])

response = client.chat(
    model="command-a-03-2025",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

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

Worth knowing

The free key is a trial key: fine for prototypes, not licensed for production.
Cohere’s own v2 endpoint lives at /v2 — /compatibility/v1 is the OpenAI-shaped one.
The Command A id is command-a-03-2025 (256K). command-a-218b is not an API id.

Models you get for free12

Command Acommand-a-03-2025
Command A+command-a-plus-05-2026
Command R+command-r-plus-08-2024
Command Rcommand-r-08-2024
Command R7Bcommand-r7b-12-2024
Command A Reasoningcommand-a-reasoning-08-2025
Command A Translatecommand-a-translate-08-2025
Embed V4embed-v4.0
Embed English V3embed-english-v3.0
Embed Multilingual V3embed-multilingual-v3.0
Rerank V3.5rerank-v3.5
Rerank English V3rerank-english-v3.0