impulse

Command R

Open weights

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.

API id command-r-08-2024Released 30 Aug 2024 (Aug 2024)
Input / 1M
$0.15
at Cohere Chat
Output / 1M
$0.60
at Cohere Chat
Context window
128K
tokens
Max output
4K
tokens per reply
Hosts
3
3 listings
Released
Aug 2024
30 Aug 2024

Pricing

List prices at Cohere Chat, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.15$0.60

What it costs a month

At Cohere Chat list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$90.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$93.60
  • Coding agent1,000 requests a day, 40K in / 2K out$216
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$504
Use your own numbers

Where to run it

3 hosts serve Command R. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
2024-08
command-r-08-2024
$0.15 / $0.60
2024-08
cohere.command-r-08-2024
$0.15 / $0.15
−43% vs headline
command-r
$0.15 / $0.60

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: CC-BY-NC-4.0
Runs in about 77.5 GB of GPU memory
Runtimes: TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • Oracle OCI
    cohere.command-r-08-2024
    $0.15 / $0.15
    43% less

Smaller Cohere models

No cheaper Cohere model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    24% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    24% less

Open-weight picks

  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    4% less
  • Ministral 14B 2512
    Mistral AI · on Mistral AI
    $0.20 / $0.20
    Has every key capability
    24% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    32% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    39% less

Call it

Using Cohere Chat's API.

Python
from litellm import completion

response = completion(
    model="cohere_chat/command-r-08-2024",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Command R cost?

On Cohere Chat, Command R costs $0.15 per million input tokens and $0.60 per million output tokens. The cheapest host is Oracle OCI (2024-08), at $0.15 per million input tokens and $0.15 per million output tokens.

Which APIs offer Command R?

Command R runs on 3 APIs: Cohere Chat, Oracle OCI and Vercel AI Gateway.

What is Command R's context window?

128K tokens, with up to 4K tokens in one reply.

Is Command R being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Command R?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (24% less), GPT-6 Luna on OpenAI (24% less) and Qwen3.8 27B on EmpirioLabs AI (4% less). Command R itself costs 43% less on Oracle OCI (2024-08). Savings are on a mix of 3 input tokens to 1 output token.

When was Command R released?

Cohere released it on 30 Aug 2024.

What is Command R's API model id?

Use command-r-08-2024 with Cohere Chat. Other hosts use their own ids: cohere.command-r-08-2024 on Oracle OCI, command-r on Vercel AI Gateway.

Sources

Raw catalog entry for command-r-08-2024 on Cohere Chat
{
  "input_cost_per_token": 1.5e-7,
  "litellm_provider": "cohere_chat",
  "max_input_tokens": 128000,
  "max_output_tokens": 4096,
  "mode": "chat",
  "output_cost_per_token": 6e-7,
  "supports_function_calling": true,
  "supports_response_schema": true,
  "supports_tool_choice": false
}