Skip to content
Metered.
Qwen (Alibaba) model

Qwen3 30B A3B Instruct 2507

API pricing per million tokens

qwen3-30b-a3b-instruct-2507 Open weightsChecked 6h ago
Cost calculator Compare
Input
$0.13
per 1M, list
Output
$0.52
per 1M tokens
Cached input
n/a
no batch tier listed
Context
262K
32K max output

Where to buy it (5)

  • StreamLakedefault region-63%$0.048 / $0.193$0.084 blended
  • DekaLLMdefault region-37%$0.09 / $0.3$0.143 blended
  • SiliconFlowfp8, fp8-37%$0.09 / $0.3$0.143 blended
  • Nebiusfp8, fp8-34%$0.1 / $0.3$0.15 blended
  • Qwen (Alibaba) (list)the lab's own API$0.13 / $0.52$0.228 blended

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $23.40 direct.

Related models

About Qwen3 30B A3B Instruct 2507

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.

Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.228 per 1M tokens at 3 input to 1 output.

OpenRouter listing Qwen (Alibaba) pricing page
Across fru.devCompany profile

Questions

How much does Qwen3 30B A3B Instruct 2507 cost?

$0.13 per million input tokens and $0.52 per million output tokens.

What is the context window of Qwen3 30B A3B Instruct 2507?

262K tokens, with up to 32K tokens of output.

Where is Qwen3 30B A3B Instruct 2507 cheapest?

Of 5 routes tracked, StreamLake is cheapest at $0.048 input and $0.193 output per million tokens.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.