ModelBench
Alibaba Qwen logo
Models/Alibaba Qwen

Qwen3 32B

Dense open Qwen model for self-hosted chat, reasoning, and coding

Source-linked qwen Open weights Released 2025-04
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.7/1M tokens
Output price$2.8/1M tokens
Context window131.072K
Max output16.384K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Model family
qwen
Knowledge cutoff
2025-04
License
Not documented
Release date
2025-04
Model ID
alibaba/qwen3-32b
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Qwen3 32B
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Deep Infra Qwen/Qwen3-32B 40.96K $0.08 $0.28 - ReasoningToolsJSON Docs
OpenRouter qwen/qwen3-32b 131.072K $0.08 $0.28 - ReasoningToolsJSON Docs
Abacus Qwen/Qwen3-32B 131.072K $0.09 $0.29 - ReasoningTools Docs
Cortecs qwen3-32b 16.384K $0.099 $0.33 - Tools Docs
LLM Gateway qwen3-32b 40.96K $0.1 $0.3 - ReasoningTools Docs
Jiekou.AI qwen/qwen3-32b-fp8 40.96K $0.1 $0.45 - Reasoning Docs
Merge Gateway qwen/qwen3-32b 131.072K $0.15 $0.6 - ReasoningTools Docs
Alibaba (China) qwen3-32b 131.072K $0.287 $1.147 - ReasoningTools Docs
Hugging Face Qwen/Qwen3-32B 131.072K $0.29 $0.59 - ReasoningToolsJSON Docs
Helicone qwen3-32b 131.072K $0.29 $0.59 - ReasoningTools Docs
Alibaba qwen3-32b 131.072K $0.7 $2.8 - ReasoningTools Docs
Pioneer Qwen/Qwen3-32B 131.072K $0.9 $0.9 $0.9 ReasoningTools Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Aider Polyglot - Unversioned - percent correctTop 8 reported models
GPT-5
88.0
o3-pro
84.9
Gemini 2.5 Pro
83.1
o3
81.3
DeepSeek Reasoner
74.2
Claude Opus 4
72.0
Claude Opus 4 (latest)
72.0
Qwen3 32B
40.0
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/alibaba/qwen3-32b
curl
curl "https://www.modelbench.lol/api/v1/models/alibaba/qwen3-32b"