cogito-v2-preview-deepseek-671b by openrouter - AI Model Details, Pricing, and Performance Metrics

deepcogito
cogito-v2-preview-deepseek-671b
deepcogito

cogito-v2-preview-deepseek-671b

completions
byopenrouter

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)

Context
163840
Input
$1.25 / 1M tokens
Output
$1.25 / 1M tokens
Accepts: text
Returns: text

Access cogito-v2-preview-deepseek-671b through LangDB AI Gateway

Recommended

Integrate with deepcogito's cogito-v2-preview-deepseek-671b and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests

Code Examples

Integration samples and API usage