DeepSeek R1 Distill Qwen-32B

Released
2025-01-20
Last refreshed
2026-10-07
Status
Researched 138d ago
Open sourceCommercial use: permittedCodingRAGLong contextClassificationJSON / Tool use
DeepSeek releases · 8 in the last 12 monthsChangelog →
Specifications
Released
2025-01-20
Context
128K
Parameters
32B
Architecture
Decoder Only
Specialization
general
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Multi-stage
Created by
DeepSeek

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website
Pricing
Output / 1M
$0.300
Input / 1M
$0.300

Cheapest of 4 routes · Novita AI

Providers(4)
Cloudflare Workers AIFireworks AINVIDIA NIMNovita AI
View 4 provider routes

About

DeepSeek R1 Distill Qwen-32B is DeepSeek's DeepSeek R1 model with an optional reasoning mode. It offers a 128K-token context window with weights openly available for self-hosting.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ B

Providers(4)

Compare all 4

Compare API pricing across 4 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Novita AI$0.300$0.300
Serverless
Fireworks AI$0.900$0.900
Serverless
Cloudflare Workers AI$0.497$4.88
Serverless
NVIDIA NIM--
ServerlessPartial

Deprecated provider routes(1)

ProviderStatusCatalog ID
OpenRouterDeprecateddeepseek/deepseek-r1-distill-qwen-32b

Available via routers & gateways(2)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughFireworks AI

NVIDIA LLM Router Blueprint

Router

NVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; being deprecated 2026-06-20.

Free OSSNVIDIA NIM

Capabilities

ReasoningStructured Outputs

Benchmark peer barsfor Coding

LiveCodeBenchRank 64 of 73
DeepSeek V4 Pro
93.5
Gemini 3.1 Pro Preview
91.7
DeepSeek V4 Flash
91.6
Qwen3.7-Max
91.6
DeepSeek R1 Distill Qwen-32Bcurrent
57.2

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
AIME 202472.6pass@1 (official DeepSeek model card)Observed 2026-10-06—Source
MATH-50094.3pass@1 (official DeepSeek model card)Observed 2026-10-06—Source
Google-Proof Q&A62.1diamondObserved 2026-10-06—Source
LiveCodeBench57.2pass@1 (official DeepSeek model card)Observed 2026-10-06—Source
Codeforces1691.0Codeforces Rating (official DeepSeek model card)Observed 2026-10-06—Source

Migration checks

No linked migration route is available for this model yet.