QwQ 32B is Alibaba's language model with a 131K context window and up to 16K output tokens, available from 7 providers, starting at $0.15 / 1M input and $0.2 / 1M output. A 32B reasoning-focused LLM from Alibaba's Qwen team, designed to match frontier closed-model performance on complex reasoning and problem-solving tasks.
Specifications
Canonical IDalibaba-qwq-32b
TypeLanguage
StatusDeprecated
CreatorAlibabaAlibaba
Providers
Context Window131K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters32B
HuggingFace Likes2,906
HuggingFace Downloads (30d)73,024
HuggingFace Downloads (all-time)2,875,672
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago
Deprecation Date
Benchmarks
Intelligence Index
13.4
#250
Math Index
29.0
#181
MMLU-Pro
0.8
#147
GPQA
0.6
#280
HLE
0.1
#186
LiveCodeBench
0.6
#97
AIME
0.8
#19
IFBench
0.4
#252
Time to First Token
0.50s
#272
SciCode
0.4
#181
MATH-500
1.0
#31
AIME 2025
0.3
#181
LCR
0.3
#242
Output TPS
31.7
#250

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
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/qwen/qwq-32b
$0.66$1.00
DeepInfra logo
DeepInfra
deepinfra/Qwen/QwQ-32B
$0.15$0.4
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwq-32b
$0.9$0.9
Hyperbolic logo
Hyperbolic
hyperbolic/Qwen/QwQ-32B
$0.2$0.2
Nebius logo
Nebius
nebius/Qwen/QwQ-32B
$0.15$0.45
Nscale logo
Nscale
nscale/Qwen/QwQ-32B
$0.18$0.2
SambaNova logo
SambaNova
sambanova/QwQ-32B
$0.5$1.00

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host QwQ 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/hrwestus2
g7e.2xlargeAWSRTX PRO Server 600096 GB$3.36/hrus-east-1
Standard_NC24ads_A100_v4AzureNVIDIA A10080 GB$3.67/hrwestus2
7 more instances can run QwQ 32B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Dolphin 2.9.2 Qwen2 72B131K$0.900$0.900Available
Cogito V1 Preview Qwen 14B131K$0.200$0.200Available
Cogito V1 Preview Qwen 32B131K$0.900$0.900Available
QwQ 32B131K$0.150$0.200Current
Qwen2.5 Coder 32B Instruct131K$0.050$0.100Available
Qwen2.5 7B Instruct131K$0.040$0.070Available
Qwen2.5 72B Instruct131K$0.120$0.300Available
QwQ 32B Preview33K$0.900$0.900Available
Qwen2.5 32B Instruct128K$0.060$0.200Available
Qwen2 72B Instruct33K$0.900$0.900Available
Qwen2.5 Coder 7B Instruct33K$0.010$0.030Available

Model IDs

@cf/qwen/qwq-32b
accounts/fireworks/models/qwq-32b
alibaba-qwq-32b
cloudflare/@cf/qwen/qwq-32b
deepinfra/Qwen/QwQ-32B
fireworks_ai/accounts/fireworks/models/qwq-32b
huggingface-llm-qwq-32b
hyperbolic/Qwen/QwQ-32B
nebius/Qwen/QwQ-32B
nscale/Qwen/QwQ-32B
qwen/qwq-32b
qwq-32b
sambanova/QwQ-32B