O

LangMart: DeepSeek: R1 Distill Qwen 14B

Openrouter
33K
Context
$0.1200
Input /1M
$0.1200
Output /1M
N/A
Max Output

LangMart: DeepSeek: R1 Distill Qwen 14B

Model Overview

Property Value
Model ID openrouter/deepseek/deepseek-r1-distill-qwen-14b
Name DeepSeek: R1 Distill Qwen 14B
Provider deepseek
Released 2025-01-29

Description

DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

Other benchmark results include:

  • AIME 2024 pass@1: 69.7
  • MATH-500 pass@1: 93.9
  • CodeForces Rating: 1481

The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Description

LangMart: DeepSeek: R1 Distill Qwen 14B is a language model provided by deepseek. This model offers advanced capabilities for natural language processing tasks.

Provider

deepseek

Specifications

Spec Value
Context Window 32,768 tokens
Modalities text->text
Input Modalities text
Output Modalities text

Pricing

Type Price
Input $0.12 per 1M tokens
Output $0.12 per 1M tokens

Capabilities

  • Frequency penalty
  • Include reasoning
  • Max tokens
  • Presence penalty
  • Reasoning
  • Repetition penalty
  • Response format
  • Seed
  • Stop
  • Structured outputs
  • Temperature
  • Top k
  • Top p

Detailed Analysis

DeepSeek-R1 (Reasoner) Model Analysis