O

LangMart: Cogito V2 Preview Llama 109B

Openrouter
Vision
33K
Context
$0.1800
Input /1M
$0.5900
Output /1M
N/A
Max Output

LangMart: Cogito V2 Preview Llama 109B

Model Overview

Property Value
Model ID openrouter/deepcogito/cogito-v2-preview-llama-109b-moe
Name Cogito V2 Preview Llama 109B
Provider deepcogito
Released 2025-09-02

Description

An instruction-tuned, hybrid-reasoning Mixture-of-Experts model built on Llama-4-Scout-17B-16E. Cogito v2 can answer directly or engage an extended “thinking” phase, with alignment guided by Iterated Distillation & Amplification (IDA). It targets coding, STEM, instruction following, and general helpfulness, with stronger multilingual, tool-calling, and reasoning performance than size-equivalent baselines. The model supports long-context use (up to 10M tokens) and standard Transformers workflows. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs

Description

LangMart: Cogito V2 Preview Llama 109B is a language model provided by deepcogito. This model offers advanced capabilities for natural language processing tasks.

Provider

deepcogito

Specifications

Spec Value
Context Window 32,767 tokens
Modalities text+image->text
Input Modalities image, text
Output Modalities text

Pricing

Type Price
Input $0.18 per 1M tokens
Output $0.59 per 1M tokens

Capabilities

  • Frequency penalty
  • Include reasoning
  • Logit bias
  • Max tokens
  • Min p
  • Presence penalty
  • Reasoning
  • Repetition penalty
  • Stop
  • Temperature
  • Tool choice
  • Tools
  • Top k
  • Top p

Detailed Analysis

Cogito v2 Preview Llama 109B MoE is an advanced Mixture-of-Experts model by DeepCogito that combines 109 billion parameters with specialized routing capabilities. Built on Llama-4-Scout-17B-16E architecture, this model represents a significant advancement in instruction-tuned, hybrid-reasoning AI systems.