QwQ 32B Check detailed information and pricing for AI models

Context Length 32,768 tokens, qwen from provided

32,768
Context Tokens
$0.15
Prompt Price
$0.40
Output Price
5/16
Feature Support

Model Overview

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

Basic Information

Developer
qwen
Model Series
Qwen
Release Date
2025-03-05
Context Length
32,768 tokens
Variant
standard

Pricing Information

Prompt Tokens
$0.15 / 1M tokens
Completion Tokens
$0.40 / 1M tokens

Supported Features

Supported (5)

Frequency Penalty
Presence Penalty
Response Format
Structured Outputs
Reasoning

Unsupported (11)

Image Input
Top K
Seed
Repetition Penalty
Min P
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Web Search Options
Top A

Other Variants

Actual Usage Statistics

#58
Out of 353 total models
30.0B
Total Tokens Last 30 Days
999.30M
Daily Average Usage
3%
Weekly Usage Change

Usage Trend for the Last 30 Days

Models by Same Author (qwen)

Qwen3 Max
256,000 tokens
$1.20 / $6.00
Qwen3 30B A3B Thinking 2507 (free)
262,144 tokens
Free
Qwen3 30B A3B Thinking 2507
262,144 tokens
$0.07 / $0.29
Qwen3 Coder 30B A3B Instruct
262,144 tokens
$0.05 / $0.21
Qwen3 30B A3B Instruct 2507
262,144 tokens
$0.05 / $0.21

Similar Price Range Models

Llama 3.3 Nemotron Super 49B v1
nvidia
131,072 tokens
$0.13 / $0.40
Rocinante 12B
thedrummer
32,768 tokens
$0.17 / $0.43
Llama 3.1 Nemotron 70B Instruct
nvidia
131,072 tokens
$0.12 / $0.30