Model Cadence
Plus $4/mo

Qwen3 30B-A3B Instruct 2507

Qwen · Released Jul 28, 2025 · Open weights
Latest Qwen3

Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Price per 1M tokens
$0.09 / $0.3
input / output · OpenRouter
Context window
262.1K
tokens in · 16.4K out
Since the last one
7 days
after Qwen3 235B-A22B Instruct 2507
Open in the timeline

Since Qwen3 235B-A22B Instruct 2507

2 releases in the Qwen3 line.

Qwen3 235B-A22B Instruct 2507Jul 21, 20257dQwen3 30B-A3B Instruct 2507Jul 28, 2025
Released7 days later
Price in / out$0.09 / $0.3−30%
Context262.1Ksame
BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

Qwen's past year

48 release days in the past year, about one every 8 days. The next is expected around Oct 30, 2026. Forecasts ↗

NovDecJanFebMarAprMayJunJulAugSepOct

Specifications

RELEASE DATEJul 28, 2025
WEIGHTSOpen weights
CONTEXT WINDOW262.1K
MAX OUTPUT16.4K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext
OUTPUTStext

Models.dev record ↗

Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.