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.

DeepSeek V4.1 Flash Add a modelChat with this model

Attribute	DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash
Specs
Context window	1M
Max output	384K
Input modalities	TextImage
Output modalities	Text
Capabilities
Streaming	Supported
Tool calling	Supported
Structured output (JSON)	Supported
Image input	Supported
Thinking mode	Supported
Price / 1M tokens
Input	$ 0.30
Output	$ 1.20
Cache read	$ 0.0060
Cache write	$ 0.30
What it is good at
Best for	Terminal and coding agents Building whole projects from scratch Agents that read screenshots and charts Hard knowledge and research High-throughput production traffic
Published benchmarks
Terminal-Bench 4.0pass_rate	42.3%Claude Code(setup not fully disclosed)
Agents' Last Examscore	35.4%(setup not fully disclosed)
ApexBench v1.1score	72.1%(setup not fully disclosed)
AutomationBench v1.0.6score	60.5%(setup not fully disclosed)
DeepSWE 1.1resolved_rate	77%Mini-SWE-V2(setup not fully disclosed)
NL2Reposcore	68.2%(setup not fully disclosed)
ProgramBenchscore	29.1%(setup not fully disclosed)
BabyVision (with tools)score	92.5%(setup not fully disclosed)
Chartography (with tools)score	83%(setup not fully disclosed)
ZeroBench main (with tools)pass_at_5	51%(setup not fully disclosed)
Humanity's Last Examaccuracy	42.6%(setup not fully disclosed)