Qwen3.8 2.4T A95B

Name: Qwen3.8 2.4T A95B
Author: Novita 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.

Context

Max output

131K

Input price

$2/1M tokens

Output price

$6/1M tokens

Capabilities

Show unsupported (3)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Details

Model IDqwen/qwen3.8-2.4t-a95b

ProviderNovita AI

CreatorAlibaba Cloud

Familyqwen3.8

License—

Statusactive

Typechat

Input modalitiestext

Output modalitiestext

Open weight—

Parameters—

Architecture—

Context window1M tokens

Max input—

Max output131K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2026-08-25

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input

Output

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: qwen3.8

Model	Caps	Perf	Speed	Context	Max out	Pricing
Qwen3.8 Flash	RTJJMS	—	—	1M	131K	$0.15$0.47
Qwen3.8 27B	RTJJMS	—	—	1M	131K	$0.42$3
Qwen3.8 2.4T A95B	RTJJMS	—	—	1M	131K	$2$6
Qwen3.8 Max	RTJJMS	—	—	1M	131K	$2$6

API

GET/v1/models/novita/qwen/qwen3.8-2.4t-a95b