Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Qwen3.6 FlashQwen3.7 Flash Add a modelChat with these 2

AttributeHide identical rows	Qwen3.6 Flashqwen/qwen3.6-flash	Qwen3.7 Flashqwen/qwen3.7-flash
Specs
Context window	1M	1M
Max output	66K	66K
Input modalities	TextImageVideo	TextImageVideo
Output modalities	Text	Text
Capabilities
Streaming	Supported	Supported
Tool calling	Supported	Supported
Structured output (JSON)	Supported	Supported
Image input	Supported	Supported
Thinking mode	Supported	Supported
Price / 1M tokens
Input	$ 0.19>= 256K$ 0.75	$ 0.040>= 32K$ 0.10>= 256K$ 0.19
Output	$ 1.13>= 256K$ 4.50	$ 0.13>= 32K$ 0.37>= 256K$ 0.74
Cache read	$ 0.019>= 256K$ 0.075	$ 0.010>= 32K$ 0.020>= 256K$ 0.040
Cache write	$ 0.24>= 256K$ 0.94	$ 0.040>= 32K$ 0.12>= 256K$ 0.24
What it is good at
Best for	Fast multimodal agents	High-volume agents Visual coding
Published benchmarks
Terminal-Bench 2.0pass_rate	51.5%Harbor/Terminus-2 · 5 runs(setup not fully disclosed)	—
SWE-Bench Proresolved_rate	49.5%(setup not fully disclosed)	—
SWE-Bench Verifiedresolved_rate	73.4%(setup not fully disclosed)	—
MMMU Proaccuracy	75.3%(setup not fully disclosed)	—
GPQA Diamondaccuracy	86%(setup not fully disclosed)	—
MCPMarkscore	37%(setup not fully disclosed)	—
VideoMMMUaccuracy	83.7%(setup not fully disclosed)	—