Qwen3 VL 30B A3B Instruct

30B / 3B
Context
131K
Max output
33K
Input price
$0.2/1M tokens
Output price
$0.7/1M tokens

Capabilities

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

Details

Model IDqwen/qwen3-vl-30b-a3b-instruct
Provider Novita AI
Familyqwen3
License—
Statusactive
Typechat
Input modalitiestext, image
Output modalitiestext
Open weight—
Parameters30B / 3B
Architecture—
Context window131K tokens
Max input—
Max output33K 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
$0.2
Output
$0.7
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: qwen3

ModelContextMax outPricing
Qwen3 4B128K8K$0.03$0.03
Qwen3 8B128K20K$0.04$0.14
Qwen3 Coder 30B A3B Instruct160K33K$0.07$0.27
qwen/qwen3-vl-8b-instruct131K33K$0.08$0.5
Qwen3 235B A22B Instruct 2507131K16K$0.09$0.58
Qwen3 30B A3B41K20K$0.09$0.45
Qwen3 32B41K20K$0.1$0.45
Qwen3 Next 80B A3B Instruct131K33K$0.15$1.5
Qwen3 Next 80B A3B Thinking131K33K$0.15$1.5
Qwen3 235B A22B41K20K$0.2$0.8
Qwen3 Coder Next262K66K$0.2$1.5
Qwen3 VL 30B A3B Instruct131K33K$0.2$0.7
qwen/qwen3-vl-30b-a3b-thinking131K33K$0.2$1
Qwen3 Omni 30B A3B Instruct66K16K$0.25$0.97
Qwen3 Omni 30B A3B Thinking66K16K$0.25$0.97
Qwen3 235B A22B Thinking 2507131K33K$0.3$3
Qwen3 VL 235B A22B Instruct131K33K$0.3$1.5
Qwen3 Coder 480B A35B Instruct262K66K$0.38$1.55
Qwen3 VL 235B A22B Thinking131K33K$0.98$3.95
Qwen3 Max262K66K$2.11$8.45

API

GET/v1/models/novita/qwen/qwen3-vl-30b-a3b-instruct