command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint the same. Read the launch post [here](https://docs.cohere.com/changelog/command-gets-refreshed). Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
Context Window
128k tokens
Max Output
4k tokens
Pricing (Input / Output)
$0.0025 / $0.01 per 1M
Architecture
transformer
Modality
text->text
curl -X POST https://api.neuralhub.xyz/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer NEURALHUB_API_KEY" \
-d '{
"model": "cohere/command-r-plus-08-2024",
"messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{ "role": "user", "content": "" }
],
"temperature": 0.7,
"max_tokens": 500,
"top_p": 0.9
}'The API returns an OpenAI-compatible response. Example:
{
"id": "chatcmpl-<uuid>",
"object": "chat.completion",
"created": 1765590291,
"model": "cohere/command-r-plus-08-2024",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The answer to life, the universe, and everything is famously 42..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 26,
"completion_tokens": 169,
"total_tokens": 195
}
}