Qwen3.8 Flash

Qwen3.8-Flash is Alibaba's multimodal MoE model and an early preview of the Qwen4 architecture: 125B total parameters with only 6B activated per token, plus a 51B N-gram embedding, built on GDN + QSA hybrid attention.

Context
1M
Max output
131K
Input price
$0.15/1M tokens
Output price
$0.47/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDqwen/qwen3.8-flash
Provider Novita AI
Creator Alibaba Cloud
Familyqwen3.8
License—
Statusactive
Typechat
Input modalitiestext, image
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window1M tokens
Max input—
Max output131K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
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
$0.15
Output
$0.47
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: qwen3.8

ModelContextMax outPricing
Qwen3.8 Flash1M131K$0.15$0.47
Qwen3.8 27B1M131K$0.42$3
Qwen3.8 2.4T A95B1M131K$2$6
Qwen3.8 Max1M131K$2$6

API

GET/v1/models/novita/qwen/qwen3.8-flash