Qwen3.8 2.4T A95Bon Krater.ai

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, with 95 billion active parameters out of 2.4 trillion total. It is

Released August 12, 2026

Specifications

Qwen3.8 2.4T A95B at a glance

Context

1M tokens

Max output

131.1K tokens

Input

Text

Output

Text

Input price

$2.00 / 1M

Output price

$6.00 / 1M

Tool callingStructured outputsReasoning support

Capabilities

What it is good at

Catalog capabilities

  • Generates text responses
  • Supports tool calling
  • Supports structured outputs

Good for

Long documentsUse with toolsStructured responsesDeep analysis

Benchmarks

Catalog data, not Krater benchmarks.

Coding index score

71.9

Agentic index score

57.1

Intelligence index score

57.7

FAQ

Questions about Qwen3.8 2.4T A95B

Clear answers based on the model catalog and Krater access.

Qwen3.8 2.4T A95B supports a context window of 1,048,576 tokens.

Use Qwen3.8 2.4T A95B in your API

Connect with Krater's unified API.

API access

Ready to use Qwen3.8 2.4T A95B?

Access leading models in one focused workspace.