qwen/qwen3-vl-30b-a3b-instruct

Chat

by 0G Foundation

Alibaba's Qwen3-VL is a multimodal vision-language model supporting text and image inputs with text output. Strong at visual reasoning, OCR, and chart/document understanding. Served via Alibaba Cloud Model Studio (DashScope, qwen3-vl-flash tier).

TEE VerifiedTeeTLSTool CallingModalities

Context

262K

262,144 tokens

Max Output

33K

32,768 tokens

Input Price

0.0400 0G

per 1M tokens

Output Price

0.4400 0G

per 1M tokens

Providers

Type

chatbot

Supported Parameters

temperaturetop_ptop_kmax_tokenspresence_penaltyseedstopstreamtoolstool_choiceresponse_format

Providers(1)

TEE (dstack)TeeTLS

Status HealthyUptime 100%Context 262KMax Out 33KIn0.0400Out0.44000G/M

Tiered Pricing (by input length)

Input ≤InputOutput

32K0.0400 0G/M0.4400 0G/M

128K0.0800 0G/M0.8800 0G/M

rest0.1600 0G/M1.7600 0G/M

View API Reference Try in Playground