Sign in Dashboard
AiTradeStore / Models / Chat / Cogito V1 Preview Qwen 32B

Cogito V1 Preview Qwen 32B

Best-in-class open-source LLM trained with IDA for alignment, reasoning, and self-reflective, agentic applications.
Chat
Code
Reasoning
Try Cogito V1 Preview Qwen 32B
API Usage
How to use Cogito V1 Preview Qwen 32BModel CardPrompting Cogito V1 Preview Qwen 32BApplications & Use Cases

API Usage

Endpoint

deepcogito/cogito-v1-preview-qwen-32B
Curl
Python
Typescript

RUN INFERENCE

curl -X POST "https://aitradestore.com/api/v1/chat/completions"  
 -H "Authorization: Bearer $AITRADESTORE_API_KEY"  
 -H "Content-Type: application/json"  
 -d '{ 
   "model": "deepcogito/deepcogito/cogito-v1-preview-qwen-32B", 
   "messages": [{"role": "user", "content": "Given two binary strings `a` and `b`, return their sum as a binary string"}] 
 }'

JSON RESPONSE

RUN INFERENCE

from aitradestore import AiTradeStore  client = AiTradeStore()
 response = client.chat.completions.create( 
   model="deepcogito/cogito-v1-preview-qwen-32B", 
   messages=[{"role": "user", "content": "Given two binary strings `a` and `b`, return their sum as a binary string"}], ) print(response.choices[0].message.content)

JSON RESPONSE

RUN INFERENCE

import AiTradeStore from "ai-tradestore";  const aitradestore = new AiTradeStore();  const response = await aitradestore.chat.completions.create({ 
   messages: [{"role": "user", "content": "Given two binary strings `a` and `b`, return their sum as a binary string"}], 
   model: "deepcogito/cogito-v1-preview-qwen-32B", });
 console.log(response.choices[0].message.content)

JSON RESPONSE

Model Provider:

Deep Cogito

Type:

Chat

Variant:

Parameters:

32B

Deployment:

✔️ Dedicated

Quantization

Context length:

128K

Pricing:

How to use Cogito V1 Preview Qwen 32B

Model details

The Cogito LLMs are instruction tuned generative models (text in/text out). All models are released under an open license for commercial use.

  • Cogito models are hybrid reasoning models. Each model can answer directly (standard LLM), or self-reflect before answering (like reasoning models).
  • The LLMs are trained using Iterated Distillation and Amplification (IDA) - an scalable and efficient alignment strategy for superintelligence using iterative self-improvement.
  • The models have been optimized for coding, STEM, instruction following and general helpfulness, and have significantly higher multilingual, coding and tool calling capabilities than size equivalent counterparts.
    • In both standard and reasoning modes, Cogito v1-preview models outperform their size equivalent counterparts on common industry benchmarks.
  • Each model is trained in over 30 languages and supports a context length of 128k.

Evaluations

We compare our models against the state of the art size equivalent models in direct mode as well as the reasoning mode. For the direct mode, we compare against Llama / Qwen instruct counterparts. For reasoning, we use Deepseek's R1 distilled counterparts / Qwen's QwQ model.

Logo

Livebench Global Average:

Logo

For detailed evaluations, please refer to the Blog Post.

Prompting Cogito V1 Preview Qwen 32B

Applications & Use Cases

Chat

AiTradeStore / Models / Chat / Cogito V1 Preview Qwen 32B

Cogito V1 Preview Qwen 32B

Best-in-class open-source LLM trained with IDA for alignment, reasoning, and self-reflective, agentic applications.
Chat
Code
Reasoning
Try Cogito V1 Preview Qwen 32B
API Usage
How to use Cogito V1 Preview Qwen 32BModel CardPrompting Cogito V1 Preview Qwen 32BApplications & Use Cases

API Usage

Endpoint

deepcogito/cogito-v1-preview-qwen-32B
Curl
Python
Typescript

RUN INFERENCE

curl -X POST "https://aitradestore.com/api/v1/chat/completions"  
 -H "Authorization: Bearer $AITRADESTORE_API_KEY"  
 -H "Content-Type: application/json"  
 -d '{ 
   "model": "deepcogito/deepcogito/cogito-v1-preview-qwen-32B", 
   "messages": [{"role": "user", "content": "Given two binary strings `a` and `b`, return their sum as a binary string"}] 
 }'

JSON RESPONSE

RUN INFERENCE

from aitradestore import AiTradeStore  client = AiTradeStore()
 response = client.chat.completions.create( 
   model="deepcogito/cogito-v1-preview-qwen-32B", 
   messages=[{"role": "user", "content": "Given two binary strings `a` and `b`, return their sum as a binary string"}], ) print(response.choices[0].message.content)

JSON RESPONSE

RUN INFERENCE

import AiTradeStore from "ai-tradestore";  const aitradestore = new AiTradeStore();  const response = await aitradestore.chat.completions.create({ 
   messages: [{"role": "user", "content": "Given two binary strings `a` and `b`, return their sum as a binary string"}], 
   model: "deepcogito/cogito-v1-preview-qwen-32B", });
 console.log(response.choices[0].message.content)

JSON RESPONSE

Model Provider:

Deep Cogito

Type:

Chat

Variant:

Parameters:

32B

Deployment:

✔️ Dedicated

Quantization

Context length:

128K

Pricing:

How to use Cogito V1 Preview Qwen 32B

Model details

The Cogito LLMs are instruction tuned generative models (text in/text out). All models are released under an open license for commercial use.

  • Cogito models are hybrid reasoning models. Each model can answer directly (standard LLM), or self-reflect before answering (like reasoning models).
  • The LLMs are trained using Iterated Distillation and Amplification (IDA) - an scalable and efficient alignment strategy for superintelligence using iterative self-improvement.
  • The models have been optimized for coding, STEM, instruction following and general helpfulness, and have significantly higher multilingual, coding and tool calling capabilities than size equivalent counterparts.
    • In both standard and reasoning modes, Cogito v1-preview models outperform their size equivalent counterparts on common industry benchmarks.
  • Each model is trained in over 30 languages and supports a context length of 128k.

Evaluations

We compare our models against the state of the art size equivalent models in direct mode as well as the reasoning mode. For the direct mode, we compare against Llama / Qwen instruct counterparts. For reasoning, we use Deepseek's R1 distilled counterparts / Qwen's QwQ model.

Logo

Livebench Global Average:

Logo

For detailed evaluations, please refer to the Blog Post.

Prompting Cogito V1 Preview Qwen 32B

Applications & Use Cases

Let's stay in touch.

Get Contact
cta-area
Company
AI Models
Use Cases

TESLA OPTIMUS HUMANOID LLC 2025. © All Rights Reserved.