Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
$0.048Input, per million tokens
$0.19Output, per million tokens
262KContext window
32KLongest answer
262K tokens of context — about 196,608 words, on a scale that ends at 2M.
What it can do
- Tool use
- Open weights
- Takes text
- Gives text
Released 29 Jul 2025 · checked 3 Oct 2026.
On these boards
More from Qwen
- Qwen3.8 Max Prime$4 in
- Qwen3.8 Omni Flash$0.15 in
- Qwen3.8 Max (0902)$2 in
- Qwen3.8 Flash$0.15 in
- Qwen3.8 27B$0.42 in
- Qwen3.8 27B (free)Free in
- Qwen3.8 2.4T A95B$2 in
- Qwen3.7 Flash$0.030 in
- Qwen3.7 Plus$0.32 in
- Qwen3.7 Max$1.48 in
- Qwen3.5 Plus 2026-04-20$0.30 in
- Qwen3.6 27B$0.32 in
- Qwen3.6 35B A3B$0.15 in
- Qwen3.6 Flash$0.19 in
- Qwen3.6 Max Preview$1.03 in
- Qwen3.6 Plus$0.33 in
- Qwen3.5-9B$0.10 in
- Qwen3.5-122B-A10B$0.26 in