All models

Qwen3 30B A3B

Qwen

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks.

Text30.5B paramsReleased 2025-04-27Hugging Face

Providers

1

Input from

$0.01/M

Output from

$0.03/M

Max context

41K

Best latency

—

Tokens processed

0

Providers (1)

Compare price, context and speed across providers serving this model.

ProviderInputOutputContextMax outputLatencyUptimeRequestsAI check
CIN_B Cheapest—
$0.01/M$0.03/M41K16K——0
40/100 Mismatch
Subscribe

Specifications

Author
Qwen
Category
Text
Input modalities
Text
Output modalities
Text
Parameters
30.5B
Max context
41K
Released
2025-04-27
Catalog ID
qwen/qwen3-30b-a3b