---
id: "qwen/qwen3-vl-235b-a22b-instruct"
also: ["qwen/qwen3-vl-235b-a22b-instruct", "Qwen/Qwen3-VL-235B-A22B-Instruct", "hf/Qwen/Qwen3-VL-235B-A22B-Instruct", "vercel/alibaba/qwen3-vl-235b-a22b-instruct"]
cheapest_list_usd_per_m: "0.2 in, 0.88 out, at deepinfra/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.1444 in, 1.8972 out, at parasail/fp8 on openrouter"
context: 262144
max_output: 32768
input: ["text", "image"]
output: ["text"]
released: "2025-09-23"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 10
gateways: "openrouter (5), vercel (3), hf (2)"
no_training: 8
trains: 0
retains_prompts: 2
---
# Qwen: Qwen3 VL 235B A22B Instruct

The Qwen3 series VL models has been comprehensively upgraded in areas such as visual coding and spatial perception. Its visual perception and recognition capabilities have significantly improved, supporting the understanding of ultra-long videos, and its OCR functionality has undergone a major enhancement.