losclouds
Model · Qwen

QwQ-32B

Open-weight reasoning specialist for math, coding, and STEM.

Pricing

Model Overview

Tracked token-pricing fields for this model family. Empty pricing fields stay hidden until the source publishes them.

Model pricing
Price fieldValue
Input$0.12 / 1M tokens
Output$0.15 / 1M tokens
SourceQwQ-32B pricing
VerifiedApr 5, 2026 (High)

Surface

Capabilities

Input and output modalities, enabled feature flags, strengths, and tradeoffs.

Model capabilities
AttributeValues
Modalities
text
to
text
Capabilities
reasoningbatchSupportpromptCachingfunctionCallingstructuredOutputs
Strengthso1-competitive math/reasoning at 32B, Apache 2.0, Very cheap via Groq
TradeoffsThinking tokens add latency, text-only

References

Official Links

Canonical launch, documentation, pricing, and release-note URLs.

Official model links
ReferenceURL
Introhttps://qwenlm.github.io/blog/qwq-32b/
Docshttps://qwenlm.github.io/blog/
Pricinghttps://www.alibabacloud.com/help/en/model-studio/model-pricing
Release notehttps://qwenlm.github.io/blog/

Coverage

Benchmark Coverage

Reported benchmark families, versions, scores, sources, and notes.

Benchmark coverage
BenchmarkVersionScoreDateSourceNotes
AIME 2024202479.5 %Mar 1, 2025Qwen TeamVendor-reported
MATH-500202490.6 %Mar 1, 2025Qwen TeamVendor-reported
GPQA202465.2 %Mar 1, 2025Qwen TeamVendor-reported

Lifecycle

Release History

Lifecycle transitions and release timeline for this model family.

Release history
ReleaseAliasLifecycleRelease DateDeprecationShutdownSummary
QwQ-32Bqwq-32bActiveMar 5, 2025——Current published model family snapshot.

Surfaces

Host Coverage

Provider-specific hosting, context, pricing notes, feature differences, and provider-status context.

Host coverage
HostTypeContextPricing NoteDifferences
Groqcloud131.1K$0.12/$0.15 per MTok.Fast inference
Alibaba DashScopefirst-party131.1K$0.29/$0.86 per MTok.—

Migration

Migration Guidance

Documented migration summary, successor families, and known breaking changes.

Migration guidance
TopicDetails
SummaryLower-priced reasoning model. Use Qwen3-235B for larger-model depth.
Replacement modelsqwen3-235b-a22b

Timeline

Change Events

Cataloged model-family updates and source references.

Change events
DateTypeTitleDescriptionSource
Mar 5, 2025family_addedQwQ-32B publishedInitial public model family launch.QwQ-32B release notes

From Qwen

Other models from Qwen

Qwen Plus 0728Qwen Plus 0728 (thinking)Qwen VL MaxQwen VL PlusQwen-MaxQwen-PlusQwen-TurboQwen2.5 72BQwen2.5 72B InstructQwen2.5 7B InstructQwen2.5 Coder 32B InstructQwen2.5 Coder 7B InstructQwen2.5 VL 32B InstructQwen2.5 VL 72B InstructQwen3 14BQwen3 235B A22B Instruct 2507Qwen3 235B A22B Thinking 2507Qwen3 235B-A22BQwen3 30B A3BQwen3 30B A3B Instruct 2507Qwen3 30B A3B Thinking 2507Qwen3 32BQwen3 8BQwen3 Coder 30B A3B InstructQwen3 Coder 480B A35BQwen3 Coder 480B A35BQwen3 Coder FlashQwen3 Coder NextQwen3 Coder PlusQwen3 MaxQwen3 Max ThinkingQwen3 Next 80B A3B InstructQwen3 Next 80B A3B InstructQwen3 Next 80B A3B ThinkingQwen3 VL 235B A22B InstructQwen3 VL 235B A22B ThinkingQwen3 VL 30B A3B InstructQwen3 VL 30B A3B ThinkingQwen3 VL 32B InstructQwen3 VL 8B InstructQwen3 VL 8B ThinkingQwen3.5 397B A17BQwen3.5 Plus 2026-02-15Qwen3.5-122B-A10BQwen3.5-27BQwen3.5-35B-A3BQwen3.5-9BQwen3.5-FlashQwen3.6 Plus