Qwen3 30B A3B Thinking 2507 Model Specs, Costs & Benchmarks (July 2026)
Qwen3 30B A3B Thinking 2507, developed by Qwen, features a context window of 81.9K tokens. The model costs $0.13 per million tokens for input and $1.56 per million tokens for output. It was released on August 28, 2025, and has achieved impressive scores in various benchmarks.
Access Qwen3 30B A3B Thinking 2507 & 210+ other AI models all in one platformTry Magica for free
Overview
 Qwen3 30B A3B Thinking 2507 | |
|---|---|
Model Provider The organization behind this AI's development | Qwen |
Input Context Window Maximum input tokens this model can process at once | 81.9K tokens |
Output Token Limit Maximum output tokens this model can generate at once | 32.8K tokens |
Release Date When this model first became publicly available | August 28, 2025 11 months ago August 28th, 2025 |
Knowledge Cutoff Latest training-data date reported by the provider | June 30, 2025 |
Pricing
| Qwen3 30B A3B Thinking 2507 | |
|---|---|
Input Token Cost Cost per million input tokens | $0.13 per million tokens |
Output Token Cost Cost per million output tokens | $1.56 per million tokens |
Capabilities & Features
| Qwen3 30B A3B Thinking 2507 | |
|---|---|
Input Types Supported input formats | text |
Output Types Supported output formats | text |
Tokenizer Text encoding system | Qwen3 |
Key Features Advanced capabilities | ✓ Function Calling✓ Structured Output✓ Reasoning Mode |
Reasoning Controls Defaults and configurable reasoning effort | Always enabled |
Open Source Model availability |
Benchmarks
| Qwen3 30B A3B Thinking 2507 | |
|---|---|
Intelligence Index Overall model quality across independent evaluations | 14.4 (Artificial Analysis index; higher is better) |
Coding Index Programming performance across independent evaluations | 12.1 (Artificial Analysis index; higher is better) |
Agentic Index Ability to complete multi-step agentic tasks | 1.8 (Artificial Analysis index; higher is better) |
Best Design Arena Score Highest human-preference Elo score across design arenas | 958 Elo (#102 in Data Viz (33.3% win rate)) |
Compare This Model
See how Qwen3 30B A3B Thinking 2507 compares with other top models
Compare Qwen3 30B A3B Thinking 2507 with top models in each category:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks
