Qwen: Qwen3 30B A3B

qwen/qwen3-30b-a3b

Qwen3 30B A3B is a 30B open-weight model (3B active per token), ranking #179 of 235 on the TryAii Score. Its best showing is #17 on MATH. It's served by 4 independent hosts from $0.12/$0.5 per million input/output tokens — a little under the going rate for its score class.

Prompt $/1M

$0.120

Completion $/1M

$0.500

Context

131,072 tok

Best provider

179 tok/s · Friendli

Specs

Model id: qwen/qwen3-30b-a3b
Display name: Qwen: Qwen3 30B A3B
Modality: text->text
Tokenizer: Qwen3
Instruct type: qwen3
Context length: 131,072
Max completion: 16,384
Prompt $/1M: $0.120
Completion $/1M: $0.500
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptyes
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Friendlifastest	179	211 ms	242 ms
DeepInfrafastest	113	408 ms	667 ms
NextBit	91	1,016 ms	1,161 ms
Alibaba	91	458 ms	509 ms
Novita	59	819 ms	1,098 ms
qwenfastest	—	—	—
Artificial Analysis	0	0 ms	—