Deep Cogito: Cogito V2 Preview Deepseek 671B
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)
Parameters
671B
Context Window
163,840
tokens
Input Price
$1.25
per 1M tokens
Output Price
$1.25
per 1M tokens
Capabilities
Model capabilities and supported modalities
Performance
Excellent reasoning capabilities with strong logical analysis
-
Specialized in code generation with excellent programming capabilities
-
Modalities
text
text
LLM Price Calculator
Calculate the cost of using this model
Monthly Cost Estimator
Based on different usage levels