Skip to content

Model Library

AlibabaReleased March 5, 2025

QwQ-32B

Alibaba · Released March 5, 2025

View public research Browse the library

Intelligence score

13

At a glance

Intelligence
13
Speed
28.8tokens/sec
Latency
2.12stime to first token
Input price
$0.66per 1M tokens
Output price
$1.00per 1M tokens
Context window
130Ktokens
Parameters
32.8billions

Summary

Comparison summary

QwQ 32B scores 13 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9). QwQ 32B generates output at 28.8 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 101.0 t/s). QwQ 32B costs $0.66 per 1M input tokens (at the higher end, median: $0.18) and $1.00 per 1M output tokens (somewhat higher than average, median: $0.40), based on the median across providers serving the model.

Specifications

Technical specifications

Model nameQwQ-32B
ProviderAlibaba
Release dateMarch 5, 2025
Intelligence score13
Speed28.8 tokens/sec
Latency (TTFT)2.12s
Input price$0.66 / 1M tokens
Output price$1.00 / 1M tokens
Context window130,000 tokens
Parameters32.8B
ReasoningYes
Input modalitiestext
Output modalities—
Open weightsYes
LicenseApache 2
API availability—
SourceModel Intelligence legacy profile: qwq-32b

Pricing

Token prices

Price per 1M tokens

QwQ-32B, as listed in the catalog record

Input $0.66 and output $1.00 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.66
  2. Output$1.00

Model Intelligence legacy profile: qwq-32b

FAQ · 19

Frequently asked questions

QwQ 32B was released on March 5, 2025.

QwQ 32B was created by Alibaba.

QwQ 32B scores 13 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9).

QwQ 32B generates output at 28.8 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 101.0 t/s).

QwQ 32B has a time to first token (TTFT) of 2.12s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight models of similar size (median: 2.09s).

QwQ 32B costs $0.66 per 1M input tokens (at the higher end, median: $0.18) and $1.00 per 1M output tokens (somewhat higher than average, median: $0.40), based on the median across providers serving the model.

QwQ 32B costs $0.66 per 1M input tokens and $1.00 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.69 per 1M tokens. Pricing may vary by provider.

Yes, QwQ 32B is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

QwQ 32B supports text input.

QwQ 32B supports text output.

No, QwQ 32B does not support image input. It can only process text.

No, QwQ 32B is not multimodal. It only supports text input.

QwQ 32B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, QwQ 32B is open weights. The model weights are publicly available and can be downloaded for self-hosting.

QwQ 32B has 32.8 billion parameters.

QwQ 32B is released under the Apache 2.0 license. This license allows commercial use.

QwQ 32B achieves a score of 13 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, QwQ 32B is available via API through 1 provider.

QwQ 32B is available through 1 API provider.