Qwen
Qwen: Qwen3 30B A3B Thinking 2507
Qwen
Input / M
Routed
Output / M
Context
Max Output
33K
Usage
Unranked
Quality
19.0 / 100
Providers
1
Best Uptime 30m
100.00%
Latency (p50)
340 ms
Throughput
143.0 tok/s
Released
August 28, 2025
Modalities
text
About
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated.
Capabilities
Vision
Tools
Reasoning
Streaming
JSON Mode
Host offerings · 1
Per-host pricing, uptime, latency, throughput
| Host | Input/M | Output/M | Context | Uptime |
|---|---|---|---|---|
| AlibabaBest Alibaba | qwen/qwen3-30b-a3b-thinking-2507 | $0.200 | $2.40 | 82K | 100.0% |
Benchmarks
Quality index 19.0 / 100
Artificial Analysis
intelligence index
14.6 / 100
coding index
12.1 / 100
agentic index
1.80 / 100
Design Arena
elo models dataviz
945.0
elo models website
941.0
Performance History
200 snapshots
Price History
Last 7 days · 0 changes
No creator-price changes in the last 7 days.
Free shows the last 7 days. Full history is a Pro feature.Get Pro
Activity Timeline
- 20d agoscore changedscore_changed
- 20d agoprice changedInput price $0.130 → $0.200
- 27d agocontext changedContext 131072 → 81920
Versus
Nearest peers by price, context, and capabilities. One click to compare.
No comparable models found.
Show this WM Score
Free live badge for your README, docs or site
Live badge — it always shows the current WM Score. Free to use anywhere, no key needed.
Markdown
[](https://whatmodel.app/models/ffd08d00-ff97-4d25-9263-4895dd100339)HTML
<a href="https://whatmodel.app/models/ffd08d00-ff97-4d25-9263-4895dd100339"><img src="https://whatmodel.app/api/public/embed/score/ffd08d00-ff97-4d25-9263-4895dd100339" alt="Qwen: Qwen3 30B A3B Thinking 2507 WM Score" height="26" /></a>Image URL
https://whatmodel.app/api/public/embed/score/ffd08d00-ff97-4d25-9263-4895dd100339First seen 43d ago · Last verified 5m ago