qwen
Qwen: Qwen3 30B A3B
qwen/qwen3-30b-a3b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3-30b-a3b is the OpenRouter listing for Qwen3-30B-A3B, a text-only causal language model from Qwen using a mixture-of-experts design with a small activated subset per token. The model card describes switchable thinking and non-thinking modes, tool calling, multilingual support, and a native context window extendable with YaRN. OpenRouter lists text input/output, reasoning enabled by default, and tool or structured-output parameters. Evidence here is mostly vendor documentation plus catalog metadata, so validate behavior on your workload.[1][2]
Strengths
- Source-reported dual thinking and non-thinking modes can trade deeper reasoning for more efficient general dialogue within one model.[1][2]
- Documented tool calling, reasoning controls, structured outputs, and broad multilingual instruction-following and translation support.[1][2]
- Mixture-of-experts design is documented with many total parameters but only a subset activated, which may help efficiency depending on serving stack.[2]
Limitations
- Evidence gap: this pack relies on vendor documentation and OpenRouter catalog data; no broad independent evaluation was supplied, so capability claims need workload validation.[1][2]
- Context reporting differs: OpenRouter lists 40,960 tokens while the model card documents 32,768 natively and 131,072 with YaRN; confirm the deployed configuration.[1][2]
- Long-context use requires YaRN setup in supported frameworks, and the vendor warns static scaling can affect shorter texts.[2]
Where to use it
- Consider for multilingual assistants or translation-oriented workflows where switching between concise chat and deliberative reasoning is useful.[2]
- Candidate for tool-using agent prototypes given documented function calling and API tool parameters; test reliability before production.[1][2]
- Potential fit for longer-document experiments only if the serving stack is configured for YaRN; benchmark quality and latency first.[2]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3 30B A3BSources checked: Nov 13, 2026
- [2] Model documentation · Qwen: Qwen3 30B A3BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- qwen/qwen3-30b-a3b
- Canonical ID
- qwen/qwen3-30b-a3b-04-28
- Creator
- qwen
- Added to OpenRouter
- 28.04.2025
- Context length
- 40,960
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.120 / out $0.500
- Knowledge cutoff
- 31.03.2025
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | models · codecategorieswin rate 37.5% · rank 139 | 932Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 39% · rank 123 | 967Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 33.9% · rank 140 | 889Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 42.4% · rank 131 | 936Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 37.7% · rank 141 | 947Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrafp8 | 40,960 | $0.120 | $0.500 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.