Alibaba Qwen: Qwen3 32B

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

Source-linked qwen Open weights Released 2025-04

API record Report

InputT

OutputT

Input price$0.7/M

Output price$2.8/M

Context131.072K

Max output16.384K

Providers14

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Qwen3 32B
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
OpenRouter	`qwen/qwen3-32b`	131.072K	16.384K	$0.08	$0.28	—	ReasoningToolsJSON	Docs ↗
Deep Infra	`Qwen/Qwen3-32B`	40.96K	16.384K	$0.08	$0.28	—	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`qwen/qwen3-32b`	40.96K	16.384K	$0.08	$0.28	—	ReasoningToolsJSON	Docs ↗
Cortecs	`qwen3-32b`	32K	32K	$0.089	$0.312	—	ReasoningToolsJSON	Docs ↗
Abacus	`Qwen/Qwen3-32B`	131.072K	8.192K	$0.09	$0.29	—	ReasoningTools	Docs ↗
Jiekou.AI	`qwen/qwen3-32b-fp8`	40.96K	20K	$0.1	$0.45	—	Reasoning	Docs ↗
Merge Gateway	`qwen/qwen3-32b`	131.072K	32.768K	$0.15	$0.6	—	ReasoningTools	Docs ↗
DigitalOcean	`alibaba-qwen3-32b`	32.768K	32.768K	$0.25	$0.55	—	ReasoningToolsJSON	Docs ↗
Alibaba (China)	`qwen3-32b`	131.072K	16.384K	$0.287	$1.147	—	ReasoningTools	Docs ↗
Helicone	`qwen3-32b`	131.072K	40.96K	$0.29	$0.59	—	ReasoningTools	Docs ↗
Hugging Face	`Qwen/Qwen3-32B`	131.072K	16.384K	$0.29	$0.59	—	ReasoningToolsJSON	Docs ↗
DevPass (LLM Gateway)	`qwen3-32b`	40.96K	16.384K	$0.36	$0.87	—	ReasoningTools	Docs ↗
Alibaba	`qwen3-32b`	131.072K	16.384K	$0.7	$2.8	—	ReasoningTools	Docs ↗
Pioneer	`Qwen/Qwen3-32B`	131.072K	8.192K	$0.9	$0.9	$0.9	ReasoningTools	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.08/M

Across 14 priced providers

Median input $0.2/M

Midpoint of listed rates

Highest input $0.9/M

11.2× the lowest listed rate

Output range $0.28 – $2.8

Per million output tokens

OpenRouter $0.08/M

Deep Infra $0.08/M

Kilo Gateway $0.08/M

Cortecs $0.089/M

Abacus $0.09/M

Jiekou.AI $0.1/M

Merge Gateway $0.15/M

DigitalOcean $0.25/M

Alibaba (China) $0.287/M

Helicone $0.29/M

Hugging Face $0.29/M

DevPass (LLM Gateway) $0.36/M

Alibaba $0.7/M

Pioneer $0.9/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

3 providers list the identical $0.08 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 32K to 131.072K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

✓ Structured output Yes

× Attachments No

× Vision input No

✓ Open weights Yes

Creator: Alibaba Qwen
Model family: qwen
Knowledge cutoff: 2025-04
License: Not documented
Release date: 2025-04
Model ID: alibaba/qwen3-32b

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

Aider Polyglot percent correct · 2025-05-08 Source ↗

Aider Polyglot #20 of 31

40.0

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Aider Polyglot, the benchmark with the widest published coverage that this model appears in.

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Jul 12, 2026Price Completion0.28 → 2.8

Jul 12, 2026Price Prompt0.08 → 0.7

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/alibaba/qwen3-32b

curl

curl "https://model.kyssta.lol/api/v1/models/alibaba/qwen3-32b"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Qwen3 32B?

Dense open Qwen model for self-hosted chat, reasoning, and coding. It is published by Alibaba Qwen and catalogued here from Models.dev.

How much does Qwen3 32B cost?

Listed input pricing starts at $0.08 per million tokens from OpenRouter, rising to $0.9 across 14 listed providers.

What is the context length of Qwen3 32B?

Qwen3 32B accepts up to 131.072K tokens of context and returns up to 16.384K output tokens.

Does Qwen3 32B support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, and reasoning.

Which providers serve Qwen3 32B?

14 providers list this model: OpenRouter, Deep Infra, Kilo Gateway, Cortecs, Abacus, Jiekou.AI and 8 more.

Are the weights for Qwen3 32B open?

Yes. The weights are published and downloadable from Hugging Face.

When was Qwen3 32B released?

The catalog records a release date of 2025-04, last verified Sep 11, 2026.

More models from Alibaba Qwen

View all →

Qwen: Qwen-Plus

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

1M ctx $0.26/M in Qwen-VL Max

Qwen vision-language model for visual reasoning, documents, and agent tasks

131.072K ctx $0.8/M in Qwen3 Coder Next

Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use

262.144K ctx $0.108/M in Qwen3.7 Max

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

1M ctx $2.5/M in