Skip to content
Metered.
Qwen (Alibaba) model

Qwen3.8 2.4T A95B

API pricing per million tokens

qwen3-8-2-4t-a95b Open weightsChecked 5h ago
Cost calculator Compare Benchmarks
Input
$2
per 1M, list
Output
$6
per 1M tokens
Cached input
$0.25
no batch tier listed
Context
1M
131K max output

Where to buy it (7)

  • DeepInfrafp4, fp4$2 / $6cached $0.2
  • Qwen (Alibaba) (list)the lab's own API$2 / $6cached $0.25
  • Modaldefault region$2 / $6cached $0.25
  • Novita AIdefault region$2 / $6cached $0.25
  • SiliconFlowfp8, fp8$2 / $6cached $0.25
  • Together AIdefault region$2 / $6cached $0.25
  • Venicedefault region$2 / $6cached $0.25

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $320.00 direct.

Related models

About Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total.

Takes text in and returns text. First listed Sep 23, 2026. Blended price $3 per 1M tokens at 3 input to 1 output. Overall score 5 on leadersboard.fru.dev (rank 27).

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

Questions

How much does Qwen3.8 2.4T A95B cost?

$2 per million input tokens and $6 per million output tokens, with cached input at $0.25.

What is the context window of Qwen3.8 2.4T A95B?

1M tokens, with up to 131K tokens of output.

Where is Qwen3.8 2.4T A95B cheapest?

Of 7 routes tracked, DeepInfra is cheapest at $2 input and $6 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.