Qwen3-VL-Flash

Copy success!

Try AIAdd to Compare

Overview

The Qwen3 series of small-scale visual understanding models effectively integrates thinking and non-thinking modes, delivering superior performance compared to the open-source Qwen3-VL-30B-A3B while maintaining fast response speeds. It features a comprehensive upgrade in image/video understanding, supporting ultra-long contexts such as extended videos and documents, spatial awareness, and object recognition across various domains. Equipped with 2D/3D visual localization capabilities, it is well-suited for tackling complex real-world tasks.

Input

TextImageVideo

Output

Text

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

Input
$0.05Per 1M tokens
Output
$0.4Per 1M tokens
Input(Implicit Cache)
$0.01Per 1M tokens
Input(Batch File)
$0.025Per 1M tokens
Output(Batch File)
$0.2Per 1M tokens
Explicit Cache Creation
$0.0625Per 1M tokens
Explicit Cache Read
$0.005Per 1M tokens

Input
$0.05Per 1M tokens
Output
$0.4Per 1M tokens
Input(Implicit Cache)
$0.01Per 1M tokens
Input(Batch File)
$0.025Per 1M tokens
Output(Batch File)
$0.2Per 1M tokens
Explicit Cache Creation
$0.0625Per 1M tokens
Explicit Cache Read
$0.005Per 1M tokens

Rate Limits & Context

Max Input
258K
Max Output
32K
Max Input (Thinking)
258K
Max Output (Thinking)
32K
Context
262K
Max Reasoning
81K
TPMTokens Per Minute
1M
RPMRequests Per Minute
1K

API Reference

Call API

Copy success!

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071

from openai import OpenAI
import os

# Initialize OpenAI client
client = OpenAI(
    api_key = os.getenv(""DASHSCOPE_API_KEY""),
    base_url=""https://dashscope-intl.aliyuncs.com/compatible-mode/v1""
)

reasoning_content = """"  # Define complete reasoning process
answer_content = """"     # Define complete response
is_answering = False    # Determine if reasoning has ended and response has started
enable_thinking = False

# Create chat completion request
completion = client.chat.completions.create(
    model=""qwen3-vl-flash"",
    messages=[
        {
            ""role"": ""user"",
            ""content"": [
                {
                    ""type"": ""image_url"",
                    ""image_url"": {
                        ""url"": ""https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg""
                    },
                },
                {""type"": ""text"", ""text"": ""How to solve this problem?""},
            ],
        },
    ],
    stream=True,
    # enable_thinking parameter enables reasoning; thinking_budget sets the maximum token count for reasoning
    # qwen-vl-plus, qwen3-vl-plus-2025-09-23 can use enable_thinking to turn reasoning on/off; qwen3-vl-235b-a22b-thinking supports enable_thinking, other Qwen-VL models do not support it
    extra_body={
        'enable_thinking': True,
        ""thinking_budget"": 500},

    # Uncomment below to return token usage in the final chunk
    # stream_options={
    #     ""include_usage"": True
    # }
)

if enable_thinking:
    print(""\n"" + ""="" * 20 + ""Reasoning Process"" + ""="" * 20 + ""\n"")

for chunk in completion:
    # If chunk.choices is empty, print usage
    if not chunk.choices:
        print(""\nUsage:"")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # Print reasoning process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # Start response
            if delta.content != """" and is_answering is False:
                print(""\n"" + ""="" * 20 + ""Complete Response"" + ""="" * 20 + ""\n"")
                is_answering = True
            # Print response process
            print(delta.content, end='', flush=True)
            answer_content += delta.content

# print(""="" * 20 + ""Complete Reasoning Process"" + ""="" * 20 + ""\n"")
# print(reasoning_content)
# print(""="" * 20 + ""Complete Response"" + ""="" * 20 + ""\n"")
# print(answer_content)