QwQ 32B

QwQ 32B is a text model from Nebius with a context window of 33K tokens and max output of 33K tokens. Pricing starts at 0.15 per million input tokens and 0.45 per million output tokens (cheapest at DeepInfra).

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keynebius/Qwen/QwQ-32B
ProviderNebius
Provider IDnebius
ModeText
Canonical Nameqwq-32b
Context Window33K tokens
Max Output33K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0001500.150
Output Tokens0.0004500.450

Benchmarks

Intelligence Index19.7#92
Math Index29.0#85
MMLU-Pro0.8#67
GPQA0.6#103
HLE0.1#55
LiveCodeBench0.6#41
AIME0.8#12
IFBench0.4#89
Time to First Token0.43s#108
SciCode0.4#65
MATH-5001.0#19
AIME 20250.3#85
LCR0.3#92

Price Comparison by Provider

Compare prices for QwQ 32B across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price, $
Output Price, $
SambaNovasambanova/QwQ-32B0.5001.00
Nscalenscale/Qwen/QwQ-32B0.1800.200
Nebiusnebius/Qwen/QwQ-32B0.1500.450
Hyperbolichyperbolic/Qwen/QwQ-32B0.2000.200
Fireworks AIfireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview0.9000.900
DeepInfradeepinfra/Qwen/QwQ-32B0.1500.400

All Variants

All available versions, regions, and API endpoints for QwQ 32B.

Model Key
Provider
Mode
Input Price, $
Output Price, $
Context
Max Output
Vision
Functions
deepinfra/Qwen/QwQ-32BDeepInfraText0.1500.400131K131Knoyes
fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-previewFireworks AIText0.9000.90033K33Knono
fireworks_ai/accounts/fireworks/models/qwq-32bFireworks AIText0.9000.900131K131Knono
hyperbolic/Qwen/QwQ-32BHyperbolicText0.2000.200131K131Knoyes
nebius/Qwen/QwQ-32BNebiusText0.1500.45033K33Knoyes
nscale/Qwen/QwQ-32BNscaleText0.1800.200N/AN/Anono
sambanova/QwQ-32BSambaNovaText0.5001.0016K16Knono