Back to Explore
Qwen: Qwen3 30B A3B Thinking 2507
Alibaba·Released 2025-08-28
Open Source30B131K ctxApache 2.0
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...
Related Models
Pricing
Input
$0.13
per 1M tokens
Output
$1.56
per 1M tokens
Blended
$0.49
per 1M tokens
Cheaper than 55% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.49
Monthly
$14.63
vs. Similar Models
Qwen: Qwen3 VL 30B A3B Thinking
$0.490%
Perceptron: Perceptron Mk1
$0.49-0%
Qwen: Qwen3 235B A22B Thinking 2507
$0.49-0%
ERNIE 4.5 300B A47B
$0.48-1%
Performance
Context Window
131K
tokens
Larger than 27% of models
Max Output
33K
tokens
25% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2
131KSame
OpenAI: gpt-oss-120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame
Open Source
apache-2.030BGGUF / GPTQ / AWQ
Downloads
762.8K
Likes
370
VRAM (FP16)
24-48 GB
GPU
A6000 / M3 Ultra