Qwen · Model guide

Qwen3.6 Flash

Q: What is Qwen3.6 Flash?

Qwen3.6 Flash is available on CrossModel as qwen/qwen3.6-flash. It has a 1M-token context window and can return up to 66K tokens per request.

Q: How much does Qwen3.6 Flash cost?

Currently $ 0.19 per 1M input tokens and $ 1.13 per 1M output tokens. Cached input is billed at $ 0.019 per 1M.

Q: Does Qwen3.6 Flash support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Q: Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Q: Can I try it without writing code?

Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Compare

qwen/qwen3.6-flash

A fast 1M-context native multimodal Qwen model for agentic coding, visual understanding and high-volume tool-driven applications, with optional reasoning and structured output.

Modalities

Context

Max output

66K

Price / 1M tokens

$ 0.19in$ 1.13out

StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA speed-oriented multimodal Agent model covering coding, reasoning and visual tasks.source

Best for

Fast multimodal agents · Designed for low-latency agent coding and visual workflows at large context sizes.(vendor claim)source

Neighbouring models

qwen/qwen3.7-flashsuccessor —Choose Qwen3.7 Flash for the current Flash generation.(vendor claim)source

Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input size	Input < 256.0K	Input ≥ 256.0K
Input	$ 0.19	$ 0.75
Output	$ 1.13	$ 4.50
Cache read	$ 0.019	$ 0.075
Cache write	$ 0.24	$ 0.94

Estimate a request

Input tokens10,000

Output tokens2,000

Cache hit rate0%

At this input size you are on the Input < 256.0K tier.

$ 0.0042

Estimated cost per request

10.0K × $ 0.19
+ 2.0K × $ 1.13

≈ $ 4.16 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window: 1.0M tokens
Max output: 65.5K tokens
Input / output modalities: Text + Image + Video → Text
Streaming: Supported
Tool calling: Supported
Structured output (JSON): Supported
Image input: Supported
Thinking mode: Supported· can be turned off
Available endpoints: /v1/chat/completions · /v1/responses · /v1/messages

First-party sources:Specsqwencloud.comCapabilitiesqwencloud.com 1 help.aliyun.com 2

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding

Terminal-Bench 2.0
pass_rate·Qwen Team · 2026-04-15Harbor/Terminus-25 runssetup not fully disclosed
Three-hour timeout and 256K context.
51.5%

Coding

SWE-Bench Pro
resolved_rate·Qwen Team · 2026-04-15setup not fully disclosed
Refined public task set; internal agent scaffold, 200K context.
49.5%
SWE-Bench Verified
resolved_rate·Qwen Team · 2026-04-15setup not fully disclosed
Qwen states that Qwen3.6-35B-A3B is served through the API as Qwen3.6-Flash; internal agent scaffold, 200K context.
73.4%

Multimodal reasoning

MMMU Pro
accuracy·Qwen Team · 2026-04-15setup not fully disclosed
75.3%

Scientific reasoning

GPQA Diamond
accuracy·Qwen Team · 2026-04-15setup not fully disclosed
The official table labels this row GPQA.
86%

Tool use

MCPMark
score·Qwen Team · 2026-04-15setup not fully disclosed
37%

Video understanding

VideoMMMU
accuracy·Qwen Team · 2026-04-15setup not fully disclosed
83.7%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code

Anthropic's official command-line coding assistant

Cursor

AI-first code editor

Cline

Open-source AI coding agent for VS Code

Codex

OpenAI's coding agent for ChatGPT desktop and the terminal

OpenCode

Open-source terminal coding assistant

Zed

High-performance, AI-native code editor

Open WebUI

Open-source, self-hosted AI chat interface

Continue

Open-source AI coding assistant for VS Code & JetBrains

See all integration guides →

Frequently asked questions

What is Qwen3.6 Flash?

Qwen3.6 Flash is available on CrossModel as qwen/qwen3.6-flash. It has a 1M-token context window and can return up to 66K tokens per request.

How much does Qwen3.6 Flash cost?

Currently $ 0.19 per 1M input tokens and $ 1.13 per 1M output tokens. Cached input is billed at $ 0.019 per 1M.

Does Qwen3.6 Flash support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Can I try it without writing code?