Loading...
Loading...
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
Input
$0.07
per 1M tokens
Output
$0.27
per 1M tokens
Blended
$0.12
per 1M tokens
Cheaper than 82% of models. Median price is $0.56/1M tokens.
Daily
$0.12
Monthly
$3.60
113
tokens/sec
Faster than 64% of models
1.50
seconds
Faster than 30% of models
1.50
seconds
Faster than 55% of models
Market Median
86 tok/s
32% faster
Median TTFT
1.07s
40% slower
Throughput/Dollar
945
tok/s per $/1M
Speed Comparison
Context Window
160K
tokens
Larger than 52% of models
Max Output
33K
tokens
20% of context
2.7M
1.1K
24-48 GB
A6000 / M3 Ultra
Quality Index
20.0
243rd of 507
Top 48%
Coding Index
19.4
204th of 417
Top 49%
Math Index
29.0
188th of 269
Top 70%
Price/1M
$0.12
115th cheapest
79% below median
Top 18%
Speed
113 tok/s
Top 36%
TTFT
1.50s
Context Window
160K
200th largest
Top 48%