Command R (08-2024) — Cohere | Modeldex

Command R (08-2024)

Active

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

Updated 4 days agoStructured data from Modeldex catalog

AgenticBudget

Knowledge cutoff

Mar 31, 2024(2.1 years ago)

API release

Aug 30, 2024(1.6 years ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

History

Command R (08-2024) became available via the Cohere API on 2024-08-30.

Training & availability

Training data has a knowledge cutoff of 2024-03-31 — information about events after that date is unlikely to appear in the model's responses. Cohere has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 128K tokens.
Max output: 4K tokens.
Input modalities: text.

Recommended for: agentic, cheap.

Limitations

The knowledge cutoff is 24 months old — this model will not know about recent events, releases, or API changes.
Text-only — cannot process images, audio, or video inputs.

Pricing

Input: $0.1500 per 1M tokens
Output: $0.6000 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="cohere/command-r-08-2024",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.15/1M

Output tokens / month2.0M

@ $0.6/1M

Input cost

$0.75

5.0M × $0.15/1M

Output cost

$1.2

2.0M × $0.6/1M

Total / month

$1.95

$23.4 / year

Providers & performance

1 provider

Multi-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.

Provider	Throughput	Latency (TTFT)	Input $ / 1M	Output $ / 1M	Context	Quant	Supports
Cohere	5tok/s	546ms	$0.15	$0.6	128K	—	tools · json

Integrations & tooling support

Tool calling: Supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.