by CohereReleased 22 September 2026
Command A+ is Cohere's flagship for business agents. It reads text and images, replies with text up to about 64 pages, uses your connected tools following the exact form you set, fills in tables as specified, and can think before answering. Use it to read a scanned form or screenshot and act on it, or to run a multi-step workflow. Command A is the text-only sibling that keeps about 256 pages in mind and replies up to about 8; pick that when you need to pack in more reading and have no images.
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 99,85 DA | 499,25 DA |
| Cached tokens read | 49,93 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| Cohere | 99,85 DA | 499,25 DA | 49,93 DA | … | … | … |
You pay the price of the provider that served your request. Prices read 15:18 · speed over the last 30 minutes · uptime over 3 days.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat LabTurn this customer email into JSON with intent, urgency and order_id.
customer-email.txtTry your own request — same model, pre-selected.
Open Chat LabSwap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
resp = client.chat.completions.create(
model="cohere/command-a-plus",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)Runs this request once on your balance.
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltyReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceAbout 0,35 DA per message. ↑ 99,85 DA · ↓ 499,25 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Command A+ is Cohere's flagship for business agents. It reads text and images, replies with text up to about 64 pages, uses your connected tools following the exact form you set, fills in tables as specified, and can think before answering. Use it to read a scanned form or screenshot and act on it, or to run a multi-step workflow. Command A is the text-only sibling that keeps about 256 pages in mind and replies up to about 8; pick that when you need to pack in more reading and have no images.
Command A costs 2,15 DA more for the same message.
Deposit dinars with your Edahabia or CIB card. Every model, Command A+ included, is paid from that balance. No foreign card, no conversion.
Cohere says it supports 48 languages, including every official European Union language, so French is covered. Arabic and Darja are not named on the page.
It reads text and images. Up to 192K tokens in one request, about 190 pages. It writes up to 48 000 words at once.
Yes, its weights are public.
Cohere. Released 22 September 2026. It knows the world up to April 2025.
Rerank 4 Fast takes a search question and a list of candidate documents and returns them ordered by relevance, reading up to about 32 pages per document, question included, in more than 100 languages. It is the lighter of the two Rerank 4 models, suited to quick replies and heavy traffic, so use it where many searches arrive at once.
You send Rerank 4 Pro a search question and a list of candidate documents, and it returns them ordered by relevance. Each document, question included, can run to about 32 pages, in more than 100 languages, and data records are accepted alongside text. Use it as a second pass after a keyword search or a search by meaning, for hard questions and long documents where result quality counts most. Rerank 4 Fast is the lighter version for quick replies; Rerank v3.5 reads only about 4 pages per document.
Cohere's earlier reranker, from before Rerank 4, reordering semantic or keyword search results by relevance and handling multi-aspect and semi-structured data across more than 100 languages
This model accepts text and pictures as input to generate numerical representations of the content. It can process up to 120 pages of material simultaneously. Its design focuses on being a fast and economical option for content representation tasks. The model is limited to processing and outputting these representations and cannot perform tasks requiring complex reasoning or generating new written material.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Open weights
Read on docs.cohere.com.
Knows events up to Apr 2025
Read on docs.cohere.com.
Run a support agent that calls your order and refund tools
Uses your tools
Translate a product catalogue into several European languages
Read a scanned delivery note and return JSON
Images · Fills your JSON