Qwen: Qwen3 30B A3B Thinking 2507

qwen/qwen3-30b-a3b-thinking-2507

Qwen3 30B A3B Thinking 2507 is a Qwen model that isn't ranked on the TryAii Score yet — no benchmark results on file. It lists at $0.2/$2.4 per million input/output tokens with a 81K-token context. It's among the fastest models we track, at roughly 73-96 tokens/sec.

Prompt $/1M

$0.200

Completion $/1M

$2.400

Context

81,920 tok

Best provider

133 tok/s · Alibaba

Specs

Model id: qwen/qwen3-30b-a3b-thinking-2507
Display name: Qwen: Qwen3 30B A3B Thinking 2507
Modality: text->text
Tokenizer: Qwen3
Instruct type: —
Context length: 81,920
Max completion: 32,768
Prompt $/1M: $0.200
Completion $/1M: $2.400
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
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
Alibabafastest	133	311 ms	366 ms
Nebius	83	539 ms	688 ms
AtlasCloudfastest	83	776 ms	928 ms
SiliconFlow	42	1,732 ms	1,999 ms
qwenfastest	—	—	—