Routeway Logo
Back to Models
DeepSeek

R1 Distill Qwen 32B

Available
Compare all DeepSeek models — V4 Pro vs Flash vs V3.2 vs V3.1 vs V3-0324

Description

DeepSeek R1 Distill Qwen 32B is a sophisticated language model designed for users who need advanced reasoning abilities. This model excels at complex problem-solving, demonstrating remarkable proficiency in tasks requiring logical deduction and critical thinking. It utilizes a distillation architecture, meaning it has learned to perform like a much larger model but in a more efficient package. DeepSeek R1 Distill Qwen 32B achieves impressive results on reasoning benchmarks, even surpassing larger models in certain areas. A standout feature is its ability to perform at a high level while being more accessible for deployment.

At a Glance

Key pricing and model details available for this model.

Input price

$0.30

per 1M tokens

Output price

$2.93

per 1M tokens

Context window

131K

tokens

Hallucination rate

14.3%

Token Pricing

Token pricing normalized to per-million-token rates.

Input / 1M tokens

$0.30

Output / 1M tokens

$2.93

Cache Read / 1M tokens

Free

Token Pricing Details

Rates are shown per 1M tokens for easier comparison.

Input / 1M tokens$0.30
Input unit1M tokens
Output / 1M tokens$2.93
Output unit1M tokens
Cache Read / 1M tokensFree
Cache Read unit1M tokens

Feature Availability

Capabilities explicitly listed in the current payload.

LLM

Available

Yes

Vision

Not listed

No

Function calling

Available

Yes

Reasoning

Available

Yes

Supported Parameters

frequency_penalty
logit_bias
max_completion_tokens
presence_penalty
reasoning_effort
response_format
stop
temperature
tool_choice
tools
top_p

Artificial Analysis

Index scores currently reported for this model.

Intelligence Index

17.2

Math Index

63

Category Radar

Aggregated from the benchmark values present for reasoning, code, math, and accuracy.

Benchmark Breakdown

Detailed benchmark results drawn from the current payload.

Intelligence Index

index

Overall 'how smart' score for an AI, combining reasoning, math, coding, and knowledge.

17.2

Reported score

Math Index

index

Composite score measuring mathematical reasoning and problem-solving.

63

Reported score

MMLU-Pro

reasoning

A broad and difficult knowledge-and-reasoning benchmark across many subjects.

73.9%

Reported score

GPQA

reasoning

Graduate-level science questions designed to be difficult to shortcut.

61.5%

Reported score

HLE

reasoning

A very hard expert-level exam across a wide range of subjects.

5.5%

Reported score

LiveCodeBench

code

Fresh programming tasks meant to test current coding ability.

27%

Reported score

SciCode

code

Coding tasks drawn from real scientific workflows.

37.6%

Reported score

MATH-500

math

A set of difficult competition-style math problems.

94.1%

Reported score

AIME

math

Advanced math competition questions.

68.7%

Reported score

AIME 2025

math

The 2025 AIME benchmark used to reduce data leakage concerns.

63%

Reported score

IFBench

accuracy

Measures how precisely the model follows detailed instructions.

22.9%

Reported score

LCR

accuracy

Tests long-context reasoning over large documents and conversations.

9.7%

Reported score

Code Samples

Quick start with the Routeway API

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: "https://api.routeway.ai/v1",
  apiKey: "<YOUR_API_KEY>",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "deepseek-r1-distill-qwen-32b",
    messages: [
      {
        role: "user",
        content: "Explain quantum computing in simple terms"
      }
    ]
  });

  console.log(completion.choices[0].message);
}

main();