Description
Cogito v2 is a multilingual, instruction-tuned Mixture of Experts (MoE) large language model with 671 billion parameters. It supports both standard and reasoning-based generation modes. The model introduces hybrid reasoning via Iterated Distillation and Amplification (IDA)—an iterative self-improvement strategy designed to scale alignment with general intelligence. Cogito v2 has been optimized for STEM, programming, instruction following, and tool use. It supports 128k context length and offers strong performance in both multilingual and code-heavy environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Deep Cogito: Cogito V2 Preview Deepseek 671B (deepcogito/cogito-v2-preview-deepseek-671b)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "deepcogito/cogito-v2-preview-deepseek-671b",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Deep Cogito: Cogito V2 Preview Deepseek 671B model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 1.25$ / 1M tokens
- Output: 1.25$ / 1M tokens
Token Limits
- Max Output: 163,840 tokens
- Max Context: 163,840 tokens
Subscription Tiers
- free
- pro
- ultimate