Cogito V2 Preview Deepseek 671B Check detailed information and pricing for AI models

Context Length 163,840 tokens, deepcogito from provided

163,840
Context Tokens
$1.25
Prompt Price
$1.25
Output Price
7/16
Feature Support

Model Overview

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)

Basic Information

Developer
deepcogito
Model Series
DeepSeek
Release Date
2025-09-02
Context Length
163,840 tokens
Variant
standard

Pricing Information

Prompt Tokens
$1.25 / 1M tokens
Completion Tokens
$1.25 / 1M tokens

Supported Features

Supported (7)

Top K
Frequency Penalty
Presence Penalty
Repetition Penalty
Min P
Logit Bias
Reasoning

Unsupported (9)

Image Input
Seed
Response Format
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A

Actual Usage Statistics

No recent usage data available.

Models by Same Author (deepcogito)

Cogito V2 Preview Llama 109B
32,767 tokens
$0.18 / $0.59

Similar Price Range Models

Weaver (alpha)
mancer
8,000 tokens
$1.13 / $1.13
Llama 3 Euryale 70B v2.1
sao10k
8,192 tokens
$1.48 / $1.48
Phi-3 Medium 128K Instruct
microsoft
128,000 tokens
$1.00 / $1.00
Sonar
perplexity
127,072 tokens
$1.00 / $1.00