Qwen: Qwen3 30B A3B Instruct 2507

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

Qwen3 30B A3B Instruct 2507 is a Qwen model that isn't ranked on the TryAii Score yet — only 2 benchmarks on file so far. It lists at $0.0481/$0.193 per million input/output tokens with a 262K-token context. It's reasonably quick at roughly 20-60 tokens/sec.

Prompt $/1M

$0.048

Completion $/1M

$0.193

Context

262,144 tok

Best provider

70 tok/s · Phala

Specs

Model id: qwen/qwen3-30b-a3b-instruct-2507
Display name: Qwen: Qwen3 30B A3B Instruct 2507
Modality: text->text
Tokenizer: Qwen3
Instruct type: —
Context length: 262,144
Max completion: 32,000
Prompt $/1M: $0.048
Completion $/1M: $0.193
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
Phala	70	1,172 ms	1,457 ms
DekaLLM	64	732 ms	972 ms
WandB	63	234 ms	286 ms
CoreWeavefastest	53	214 ms	260 ms
Nebius	47	295 ms	329 ms
Alibaba	42	334 ms	354 ms
StreamLake	30	1,173 ms	1,618 ms
Venice	16	2,933 ms	3,787 ms
SiliconFlow	14	1,473 ms	1,534 ms
AtlasCloud	11	2,221 ms	2,448 ms