DeepSeek logo

DeepSeek R1 Distill Qwen 32B

Pricing & Specs API
Free REST API for prices, specs and benchmarks
DeepSeek R1 Distill Qwen 32B is DeepSeek's language model with a 131K context window and up to 32K output tokens, available from 5 providers, starting at $0.15 / 1M input and $0.15 / 1M output. A 32B Qwen-based model distilled from DeepSeek R1's reasoning capabilities, offering high-quality chain-of-thought performance at a mid-scale parameter count.
Specifications
Canonical IDdeepseek-r1-distill-qwen-32b
TypeLanguage
StatusActive
CreatorDeepSeekDeepSeek
Providers
Context Window131K tokens
Max Output32K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters32B
HuggingFace Likes1,545
HuggingFace Downloads (30d)1,046,750
HuggingFace Downloads (all-time)23,929,632
Release Date · 2 years ago
Knowledge Cutoff · 2 years ago
Benchmarks
Intelligence Index
#368
Math Index
#143
MMLU-Pro
#201
GPQA
#332
HLE
#426
LiveCodeBench
#242
AIME
#51
IFBench
#403
Time to First Token
#95
SciCode
#221
MATH-500
#57
AIME 2025
#143
LCR
#399
Output TPS
#355

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cloudflare Workers AI logo
Cloudflare Workers AI
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
$0.497$4.88
DeepInfra logo
DeepInfra
deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
$0.27$0.27
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b
$0.9$0.9
Novita logo
Novita
novita/deepseek/deepseek-r1-distill-qwen-32b
$0.3$0.3
Nscale logo
Nscale
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
$0.15$0.15

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek R1 Distill Qwen 32B, ranked by cheapest on-demand price. The model needs about 77 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP20sAzure2× AMD Alveo U250 FPGA (64GB)128 GB$3.30/hr
g7e.2xlargeAWSRTX PRO Server 600096 GB$3.36/hr
Standard_NC24ads_A100_v4AzureNVIDIA A10080 GB$3.67/hr
7 more instances can run DeepSeek R1 Distill Qwen 32B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek R1T2 Chimera164K——Available
DeepSeek R1 528164K$0.200$0.250Deprecated
DeepSeek R1 Distill Qwen 32B131K$0.150$0.150Current
DeepSeek R1 Distill Llama 70B131K$0.200$0.375Deprecated
DeepSeek R1164K$0.280$0.400Deprecated
DeepSeek R1 Distill Qwen 14B—131K$0.070$0.070Deprecated
DeepSeek R1 Distill Llama 8B—131K$0.025$0.025Available
DeepSeek R1 Distill Qwen 1.5B—131K$0.090$0.090Deprecated
DeepSeek R1 528 Turbo—33K$1.00$3.00Available
DeepSeek R1 528B—128K——Deprecated
DeepSeek R1 671B—131K$0.800$0.800Available

Model IDs

@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
accounts/fireworks/models/deepseek-r1-distill-qwen-32b
cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
deepseek-llm-r1-distill-qwen-32b
deepseek-r1-distill-qwen-32b
deepseek/deepseek-r1-distill-qwen-32b
fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b
novita/deepseek/deepseek-r1-distill-qwen-32b
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B