Cogito v2 405B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. It represents a significant step toward frontier intelligence with dense architecture delivering performance competitive with leading closed models. This advanced reasoning system combines policy improvement with massive scale for exceptional capabilities.
Context Window
33k tokens
Pricing (Input / Output)
$0.0035 / $0.0035 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": "deepcogito/cogito-v2-preview-llama-405b",
"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": 1765590405,
"model": "deepcogito/cogito-v2-preview-llama-405b",
"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
}
}