Model profile
qwen

Qwen: Qwen3 30B A3B

Qwen: Qwen3 30B A3B is a budget text-first model from qwen with a balanced runtime profile, standard context posture, and the clearest fit around long-context research / multimodal.

Best for: Long-context research / MultimodalBalanced latencyStandard contextBudget pricing
Intelligence
15.3

Benchmark blend

Coding
11.0

Dev workflow signal

Context
41K Tokens

Standard

Input Price
$0.20

Budget tier

Decision snapshot
40

Qwen: Qwen3 30B A3B currently reads as a budget text-first option with standard context and a balanced runtime profile.

Overall profile
Use-case specific
Best for
Long-context research / Multimodal
Latency tier
Balanced
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
15.3
15

General reasoning and benchmark headroom.

Limited
Speed
63 tok/s
63

TTFT 1.07s

Competitive
Context
41K Tokens
48

How much prompt and task state can stay in view.

Situational
Price
$0.20
86

$2.40 output / 1M

Efficient

Editorial Profile

Qwen: Qwen3 30B A3B in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score 11Math score 72

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.

Identity

qwen text-first profile

Positioning

Long-context research / Multimodal with standard context and balanced runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths
  • The available source data suggests a balanced profile rather than one dominant edge.

Tradeoffs
  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Latency is balanced rather than ultra-fast, which is fine for most workflows but not the snappiest tier.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

  • Context window is more comfortable for focused tasks than extremely long sessions.

Best fit
  • Focused chat, retrieval-augmented flows, and narrower production tasks.

Compare Next

Similar profiles worth opening next

qwen

Qwen: Qwen3.5 397B A17B

Intelligence
45.0
Context
262K Tokens
Input Price
$0.60
qwen

Qwen: Qwen3.5-122B-A10B

Intelligence
41.6
Context
262K Tokens
Input Price
$0.40
qwen

Qwen: Qwen3 Max Thinking

Intelligence
39.9
Context
262K Tokens
Input Price
$1.20

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

Intelligence Index
15.3
MMLU Pro
77.7%
GPQA
61.6%
HLE
6.6%
Coding

Software implementation, debugging quality, and coding benchmark signal.

Coding Index
11.0
LiveCodeBench
0.506
SciCode
28.5%
Math

Formal reasoning, structured problem solving, and competition-style math.

Math Index
72.3
AIME
75.3%
AIME 2025
72.3%
Math 500
95.9%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
41.5%
TAU2
26.0%
TerminalBench Hard
2.3%
LCR
0.0%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
41K Tokens
Vision
Text-first
Modalities
text->text, text
Tokenizer
Qwen3
Max Completion
40960
Moderation
No
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Input Modalities
text
Output Modalities
text
Price architecture
Input
per 1M input tokens
$0.20
Output
per 1M output tokens
$2.40
Blended
AA 3:1 mix
$0.75

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.