ZMIME
Alibaba (Qwen) · Released Sep 17, 2024

Qwen2.5 32B Instruct

Qwen instruction model for multilingual chat, reasoning, and tool use.

  • Open weights
  • Tool calling
  • Retired
Capability
128.5ECI · #138 of 158
Input
$0.70per 1M tokens
Output
$2.80per 1M tokens
Context
131K8K max output

Retired Qwen2.5 32B Instruct is no longer offered by Alibaba (Qwen) or any API host we track (since Nov 2, 2026). The specs and prices below are its last published listing, kept for reference.

Pricing

What it costs

Input
$0.70per million tokens
Output
$2.80per million tokens
Blended (3:1)
$1.23pricier than 62% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$2.80
Team assistant25M input + 5M output tokens$31.50
Production app250M input + 50M output tokens$315.00

Official Alibaba API price, as listed on models.dev.

Capability

Independent benchmarks

128.5Epoch Capabilities Index
#138 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (123.5–130.0); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions46.1%
  • OTIS Mock AIME 2024–2025Competition mathematics7.4%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
Sep 17, 2024
Knowledge cutoff
Apr 2024
Context window
131,072 tokens
Max output
8,192 tokens
Inputs
Text
Output
Text
Reasoning
No
Tool calling
Yes
Structured output
No
Weights
Open weights
API model ID
qwen2-5-32b-instructon Alibaba
Availability
1 API providerlisted on models.dev
Status
Retired no provider has listed it since Nov 2, 2026

Alibaba model documentation

Same lab

More from Alibaba (Qwen)

Questions

About Qwen2.5 32B Instruct

Is Qwen2.5 32B Instruct still available?

No. Qwen2.5 32B Instruct has been retired: neither Alibaba (Qwen) nor any API host we track lists it since Nov 2, 2026. This page keeps its last published specs and prices for reference.

How much does Qwen2.5 32B Instruct cost?

Qwen2.5 32B Instruct costs $0.70 input / $2.80 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $1.23 per million tokens, more expensive than 62% of the 469 priced models we track.

What is the context window of Qwen2.5 32B Instruct?

Qwen2.5 32B Instruct accepts up to 131,072 tokens per request and can write up to 8,192 tokens in one response.

How good is Qwen2.5 32B Instruct?

Epoch AI gives Qwen2.5 32B Instruct a Capabilities Index score of 128.5 (likely range 123.5–130.0), ranking it #138 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 46.1%, OTIS Mock AIME 2024–2025 7.4%.

Is Qwen2.5 32B Instruct open source?

Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.

What inputs does Qwen2.5 32B Instruct support?

Qwen2.5 32B Instruct accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.

When was Qwen2.5 32B Instruct released?

Alibaba (Qwen) released Qwen2.5 32B Instruct on Sep 17, 2024. Its training data runs to Apr 2024.

What are the best alternatives to Qwen2.5 32B Instruct?

The closest current models from other labs on capability, price and release date are Mistral Large 2.1 (Mistral AI, $2.00 / $6.00), Llama-3.3-70B-Instruct (Meta, ECI 126.2, $0.59 / $0.745), Nova Pro (Amazon, $0.80 / $3.20) and Claude Haiku 3.5 (Anthropic, ECI 124.8, $0.80 / $4.00).