Cogito V2 Preview Llama 109B

About Cogito V2 Preview Llama 109B

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](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Other Model Lineup

Compare all models from Other to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Qwen2.5 72B Instruct

Alibaba Qwen

Input: $0.36

Output: $0.40

Context: 33k

Rocinante 12B

Thedrummer

Input: $0.25

Output: $0.50

Context: 66k

Qwen3 VL 30B A3B Instruct

Alibaba Qwen

Input: $0.15

Output: $0.60

Context: 262k

Llama 4 Maverick

Meta

Input: $0.15

Output: $0.60

Context: 1.0M

💡 Cheaper Alternatives

Same Brand (Other)

Cross Brand

🚀 Quick Start

Get started with Cogito V2 Preview Llama 109B API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepcogito/cogito-v2-preview-llama-109b-moe",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision