Models / Alibaba / Qwen3-Coder 30B-A3B Instruct

Alibaba · qwen

Qwen3-Coder 30B-A3B Instruct

Smaller Qwen coder for efficient local agents and repo-level fixes

$0.45 in · $2.25 out

per 1M tokens · first-party price. Reference price from Alibaba, the lab's own listing.

Provider input prices run from $0.07 to $0.45 per 1M tokens. Output prices run from $0.26 to $2.25.

Context
262,144
Max output
65,536
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Apr 1, 2025
Updated in source
Apr 1, 2025
Knowledge
2025-04
Providers
14

Higher rates apply above 32,000, 128,000 input tokens. The calculator switches to that rate when the input is longer.

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
DevPass$0.07$0.27———
Hugging Face$0.07$0.26———
Kilo Gateway$0.07$0.28———
LLM Gateway$0.07$0.27———
OpenRouter$0.07$0.28———
NanoGPT$0.10$0.40$0.05——
Amazon Bedrock$0.15$0.60———
Cortecs$0.18$0.70$0.014——
Scaleway$0.20$0.80———
Alibaba$0.22$0.86———
Eden AI$0.22$0.90———
GreenPT$0.29$1.08———
Alibabareference$0.45$2.25———
Pendra$0$0———

Jobs this model qualifies for