QwQ-32B
Reasoning
Qwen's reasoning variant, open-weights chain-of-thought at 32B.
QwQ-32B is a reasoning AI model from Qwen. It costs $0.6000 per million input tokens and $2.40 per million output tokens (blended $1.14/M), with a 131,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
INPUT
$0.6000/M
per million input tokens
OUTPUT
$2.40/M
per million output tokens
CONTEXT
131,000
tokens
Hand-maintained from Qwen's published pricing; no check date on record.
What it is good at
- Open reasoning
- Visible thinking
- 131K context
Typical use cases
- Reasoning research
- Self-hosted reasoning agents
Benchmarks
vs. best public score
LMArena Elo1336 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.
More from Qwen
See all 22 →Qwen3.7-Max
Flagship · 1,000,000 ctx
in $2.50/Mout $7.50/M
Qwen3.7-Plus
Balanced · 1,000,000 ctx
in $0.4000/Mout $1.60/M
Qwen2.5-Max
Flagship · 32,000 ctx
in $1.60/Mout $6.40/M
Qwen2.5-72B-Instruct
Large · 128,000 ctx
in $0.3600/Mout $0.4000/M
Qwen2.5-32B-Instruct
Balanced · 128,000 ctx
in $0.7000/Mout $0.7000/M
Qwen2.5-14B-Instruct
Small · 128,000 ctx
in $0.3500/Mout $0.3500/M
Frequently asked questions
How much does QwQ-32B cost?
QwQ-32B costs $0.6000 per million input tokens and $2.40 per million output tokens, for a blended reference rate of $1.14 per million tokens.
What is QwQ-32B's context window?
QwQ-32B supports up to 131,000 tokens of context in a single request.
What is QwQ-32B best for?
QwQ-32B is well suited to Open reasoning, Visible thinking and 131K context.
Who makes QwQ-32B?
QwQ-32B is developed and served by Qwen.
