Alibaba Qwen: Qwen3 30B A3B

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Source-linked qwen Open weights Released 2025-04-28

API record Report

InputT

OutputT

Input price$0.08/M

Output price$0.29/M

Context131.072K

Max output16.384K

Providers8

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 30B A3B
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Helicone	`qwen3-30b-a3b`	41K	41K	$0.08	$0.29	—	Tools	Docs ↗
Jiekou.AI	`qwen/qwen3-30b-a3b-fp8`	40.96K	20K	$0.09	$0.45	—	Reasoning	Docs ↗
NanoGPT	`qwen/qwen3-30b-a3b`	41K	32.768K	$0.1	$0.3	$0.05	Not listed	Docs ↗
Merge Gateway	`qwen/qwen3-30b-a3b`	131.072K	32.768K	$0.108	$1.076	$0.022	ReasoningTools	Docs ↗
Hugging Face	`Qwen/Qwen3-30B-A3B`	40.96K	16.384K	$0.12	$0.5	—	ReasoningToolsJSON	Docs ↗
Deep Infra	`Qwen/Qwen3-30B-A3B`	40.96K	16.384K	$0.12	$0.5	—	ReasoningToolsJSON	Docs ↗
OpenRouter	`qwen/qwen3-30b-a3b`	131.072K	8.192K	$0.13	$0.52	—	ReasoningTools	Docs ↗
Kilo Gateway	`qwen/qwen3-30b-a3b`	131.072K	8.192K	$0.13	$0.52	—	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 8 priced providers

Median input $0.114/M

Midpoint of listed rates

Highest input $0.13/M

1.6× the lowest listed rate

Output range $0.29 – $1.076

Per million output tokens

Helicone $0.08/MLowest

Jiekou.AI $0.09/M

NanoGPT $0.1/M

Merge Gateway $0.108/M

Hugging Face $0.12/M

Deep Infra $0.12/M

OpenRouter $0.13/M

Kilo Gateway $0.13/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.

Context limits also differ by provider, from 40.96K 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 No

× Tool calling No

× Structured output No

× Attachments No

× Vision input No

✓ Open weights Yes

Creator: Alibaba Qwen
Model family: qwen
Knowledge cutoff: Not documented
License: Not documented
Release date: 2025-04-28
Model ID: alibaba/qwen3-30b-a3b

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

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

No changes recorded

This record has not changed within the retained import history.

Provenance

Sources & verification

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

Methodology

Last verified: Aug 17, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Models.devcatalog ↗Helicone documentationprovider documentation ↗Jiekou.AI documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗Merge Gateway documentationprovider documentation ↗Hugging Face documentationprovider documentation ↗Deep Infra documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗

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://www.modelbench.lol/api/v1/models/alibaba/qwen3-30b-a3b

curl

curl "https://www.modelbench.lol/api/v1/models/alibaba/qwen3-30b-a3b"

Common questions

Frequently asked questions

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

What is Qwen3 30B A3B?

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning. It is published by Alibaba Qwen and catalogued here from Models.dev.

How much does Qwen3 30B A3B cost?

Listed input pricing starts at $0.08 per million tokens from Helicone, rising to $0.13 across 8 listed providers.

What is the context length of Qwen3 30B A3B?

Qwen3 30B A3B accepts up to 131.072K tokens of context and returns up to 16.384K output tokens.

Which providers serve Qwen3 30B A3B?

8 providers list this model: Helicone, Jiekou.AI, NanoGPT, Merge Gateway, Hugging Face, Deep Infra and 2 more.

Are the weights for Qwen3 30B A3B open?

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

When was Qwen3 30B A3B released?

The catalog records a release date of 2025-04-28, last verified Aug 17, 2026.