Qwen: Qwen3.8 Omni Flash

apache-2.0

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding.

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
Fine-tuning

Details

Model IDqwen/qwen3.8-omni-flash
Provider OpenRouter
Creator Qwen
Familyqwen3.8
Licenseapache-2.0
Status—
Typechat
Input modalitiestext, image, audio, video
Output modalitiestext
Open weightYes
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

Pricing

Input
$0.15
Output
$0.47
Cache write
—
Cache read
$0.02
Batch in
—
Batch out
—

Family Comparison: qwen3.8

ModelContextMax outPricing
Qwen: Qwen3.8 27B (free)262K236K—
Qwen: Qwen3.8 27B1M236K$0.15$1.88
Qwen: Qwen3.8 Flash1M131K$0.15$0.47
Qwen: Qwen3.8 Omni Flash1M131K$0.15$0.47
Qwen: Qwen3.8 2.4T A95B (batch)1.0M909K$2$6
Qwen: Qwen3.8 2.4T A95B1.0M131K$2$6
Qwen: Qwen3.8 Max (0902)1M131K$2$6
Qwen: Qwen3.8 Max1M131K$2$6
Qwen: Qwen3.8 Max Prime1M131K$4$12

API

GET/v1/models/openrouter/qwen/qwen3.8-omni-flash

Qwen: Qwen3.8 Omni Flash

qwen/qwen3.8-omni-flash

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding.

Changes · 2 entries
qwen/qwen3.8-omni-flashcreateca7a400Nov 2, 2026, 03:02 AM
qwen/qwen3.8-omni-flashcreate28ec4f5Sep 23, 2026, 06:40 AM