Command A Reasoning 08-2025

Command A Reasoning 08 is a Cohere model for enterprise language, retrieval, multilingual, or embedding workloads.

Input / output price: $2.50 / $10.00 per 1M
Context: 289K tokens
Released: Aug 21, 2025

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "cohere/command-a-reasoning-08-2025".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="cohere/command-a-reasoning-08-2025",

    messages=[{"role": "user", "content": "Hello!"}],

)

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

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "cohere/command-a-reasoning-08-2025",

  messages: [{ role: "user", content: "Hello!" }],

});

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

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "cohere/command-a-reasoning-08-2025",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Cohere`cohere/command-a-reasoning-08-2025`	289K	$2.50/M	$10.00/M	$0.25/M

Is a provider down? Cohere status

Pricing

USD per 1M tokens on Cohere, after gateway discounts.

Input: $2.50 per 1M
Output: $10.00 per 1M
Cache read: $0.25 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$2.50/MCohere

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

100tokens/sacross providers

Faster than 70% of the other 329 models on the gateway

Response latency

Lower is better

1.3sacross providers

Faster than 70% of the other 375 models on the gateway

Benchmarks

5 published scores from 1 source, each linked to where it was published.

Published scores

Benchmark	Score	Source	Published
SciCodecohere.com	30%	cohere.com	May 20, 2026
Terminal-Bench Hardcohere.com	3%	cohere.com	May 20, 2026

Benchmark	Score	Source	Published
Tau2-bench Telecomcohere.com	37%	cohere.com	May 20, 2026

Benchmark	Score	Source	Published
AIME 2025cohere.com	57%	cohere.com	May 20, 2026

Benchmark	Score	Source	Published
IFBenchcohere.com	36%	cohere.com	May 20, 2026

Apps

Use Command A Reasoning 08-2025 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Command A Reasoning 08-2025 FAQ

Short answers, built from the data on this page.

Command A Reasoning 08-2025 is a model from Cohere, released on Aug 21, 2025. Command A Reasoning 08 is a Cohere model for enterprise language, retrieval, multilingual, or embedding workloads.

On the Respan gateway, Command A Reasoning 08-2025 costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on Cohere, after gateway discounts.

Command A Reasoning 08-2025 is served by Cohere.

Command A Reasoning 08-2025 accepts up to 289K tokens of context.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "cohere/command-a-reasoning-08-2025". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Command A Reasoning 08-2025 has 5 published benchmark scores, including SciCode 30%, Tau2-bench Telecom 37%, and AIME 2025 57%. Each score links to where it was published; the data is collected by Respan.