Qwen3.5 122B A10B

Name: Qwen3.5 122B A10B
Author: Novita AI

122B / 10B

The Qwen3.5-122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

Context

262K

Max output

66K

Input price

$0.4/1M tokens

Output price

$3.2/1M tokens

Capabilities

Show unsupported (3)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Details

Model IDqwen/qwen3.5-122b-a10b

ProviderNovita AI

CreatorAlibaba Cloud

Familyqwen3.5

License—

Statusactive

Typechat

Input modalitiestext, image

Output modalitiestext

Open weight—

Parameters122B / 10B

Architecture—

Context window262K tokens

Max input—

Max output66K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2026-02-26

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

$0.4

Output

$3.2

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: qwen3.5

Model	Caps	Perf	Speed	Context	Max out	Pricing
Qwen3.5-Plus	RTJJMS	—	—	1M	66K	—
Qwen3.5 35B A3B	RTJJMS	—	—	262K	66K	$0.25$2
Qwen3.5 27B	RTJJMS	—	—	262K	66K	$0.3$2.4
Qwen3.5 122B A10B	RTJJMS	—	—	262K	66K	$0.4$3.2
Qwen3.5 397B A17B	RTJJMS	—	—	262K	66K	$0.6$3.6

API

GET/v1/models/novita/qwen/qwen3.5-122b-a10b