Qwen3 30B A3B

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.

Significantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.

alibaba/qwen3-30b-a3b

Organization: Alibaba
Family: qwen
Providers: 14
Context: 131,072
Output limit: 16,384
Knowledge: —
Release: 2025-04-28
Updated: —
Weights: Open
Input: text
Output: text
Capabilities: —

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

14 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	qwen3-30b-a3b	128,000	8,192	— / —	—	—	—	View
Cloudflare Workers AI	@cf/qwen/qwen3-30b-a3b-fp8	32,768	32,768	— / —	—	—	—	View
Deep Infra	Qwen/Qwen3-30B-A3B	40,960	16,384	— / —	—	—	—	View
DevPass (LLM Gateway)	qwen3-30b-a3b	32,768	16,384	— / —	—	—	—	View
Helicone	qwen3-30b-a3b	41,000	41,000	— / —	—	—	—	View
Hugging Face	Qwen/Qwen3-30B-A3B	40,960	16,384	— / —	—	—	—	View
Jiekou.AI	qwen/qwen3-30b-a3b-fp8	40,960	20,000	— / —	—	—	—	View
Kilo Gateway	qwen/qwen3-30b-a3b	40,960	16,384	— / —	—	—	—	View
LLM Gateway	greenference/qwen3-30b-a3b	8,192	4,096	— / —	—	—	—	View
Merge Gateway	qwen/qwen3-30b-a3b	131,072	32,768	— / —	—	—	—	View
NanoGPT	qwen/qwen3-30b-a3b	41,000	32,768	— / —	—	—	—	View
DeepInfravia OpenRouter	qwen/qwen3-30b-a3b fp8	40,960	16,384	$0.12 / $0.50	Yes	Yes	Yes	View
Qiniu	qwen3-30b-a3b	40,000	4,096	— / —	—	—	—	View
Vercel AI Gateway	alibaba/qwen-3-30b	40,960	16,384	— / —	—	—	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.12Per 1M input tokens

Output from$0.50Per 1M output tokens

Available offers14Across 14 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 1 lowest-priced configuration

InputOutput

DeepInfradeepinfra/fp8

$0.12$0.50

qwen/qwen3-30b-a3bObserved Oct 10, 2026, 11:31 AM UTC

Input: $0.12
Output: $0.50

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
DeepInfradeepinfra/fp8	$0.12	$0.50	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

DeepInfradeepinfra/fp8

492–2,083.24 ms

All latency percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/fp8	492 ms	799 ms	1,202.8 ms	2,083.24 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

DeepInfradeepinfra/fp8

96–136.6 t/s

All throughput percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/fp8	96 t/s	114 t/s	125 t/s	136.6 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 1 endpoint

Endpoint5 minutes30 minutes24 hours

DeepInfradeepinfra/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

qwen/qwen3-30b-a3bObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 10

Intelligence

7.6

Design Arena	Category	Elo	Win rate	Rank
models	codecategories	946	37.5%	123
models	dataviz	969	39%	114
models	gamedev	906	33.9%	126
models	uicomponent	949	42.4%	114
models	website	959	37.7%	127

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineQwen: Qwen3 30B A3B

46.667%

gpqa diamondQwen: Qwen3 30B A3B

60.943%

Evaluation	Configuration	Source	Results	Details
models · uicomponent	Qwen3 30B-A3Bqwen/qwen3-30b-a3b-04-28	Design Arena	943 Elo	Details
Composite indices	Qwen3 30B A3B (Reasoning)qwen/qwen3-30b-a3b-04-28	Artificial Analysis	Intelligence 7.6 · Coding — · Agentic —	Details
tau bench verified airline	Qwen: Qwen3 30B A3Bqwen/qwen3-30b-a3b-04-28	OpenRouter	46.667%	Details
models · dataviz	Qwen3 30B-A3Bqwen/qwen3-30b-a3b-04-28	Design Arena	967 Elo	Details
models · website	Qwen3 30B-A3Bqwen/qwen3-30b-a3b-04-28	Design Arena	955 Elo	Details
gpqa diamond	Qwen: Qwen3 30B A3Bqwen/qwen3-30b-a3b-04-28	OpenRouter	60.943%	Details
models · codecategories	Qwen3 30B-A3Bqwen/qwen3-30b-a3b-04-28	Design Arena	942 Elo	Details
models · gamedev	Qwen3 30B-A3Bqwen/qwen3-30b-a3b-04-28	Design Arena	899 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

qwen/qwen3-30b-a3bObserved Oct 10, 2026, 11:31 AM UTC

Context: 40,960
Maximum output: 16,384
Tokenizer: Qwen3
Input: text
Output: text
Moderation: No
Instruction format: qwen3
Knowledge cutoff: 2025-03-31
Added to OpenRouter: 2025-04-28

Base URLhttps://openrouter.ai/api/v1

Model IDqwen/qwen3-30b-a3b

Version IDqwen/qwen3-30b-a3b-04-28

Weights IDQwen/Qwen3-30B-A3B

Reasoning

Required: No
Enabled by default: Yes
Default effort: —
Supported efforts: —

Supported parameters

frequency_penalty
include_reasoning
logit_bias
max_tokens
min_p
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Qwen3 30B A3B cost?

Listed rates start at $0.12 per million input tokens and $0.50 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Qwen3 30B A3B?

There are 14 cataloged offers across 14 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 131,072 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 3 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Oct 20, 2026 · 26f9b04babb8
Sep 14, 2026 · 7578d7f367e1
Sep 12, 2026 · 00f193f0da13