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.

Qwen3.8 Flash Add a modelChat with this model

Attribute	Qwen3.8 Flashqwen/qwen3.8-flash
Specs
Context window	1M
Max output	131K
Input modalities	TextImageVideo
Output modalities	Text
Capabilities
Streaming	Supported
Tool calling	Supported
Structured output (JSON)	Supported
Image input	Supported
Thinking mode	Supported
Price / 1M tokens
Input	$ 0.13
Output	$ 0.43
Cache read	$ 0.016
Cache write	$ 0.20
What it is good at
Best for	High-concurrency workloads Coding and cowork agents Million-token context
Published benchmarks
Agents' Last Examscore	51.2%(setup not fully disclosed)
DeepSWE 1.1resolved_rate	58.7%(setup not fully disclosed)
LiveCodeBench v6pass_rate	91.9%(setup not fully disclosed)
SWE-Bench Multilingualresolved_rate	81%mini-swe-agent(setup not fully disclosed)
SWE-Bench Proresolved_rate	62.5%Claude Code(setup not fully disclosed)
AndroidWorldsuccess_rate	84.5%(setup not fully disclosed)
CharXiv Reasoning (no tools)accuracy	84.6%(setup not fully disclosed)
Humanity's Last Examaccuracy	35.9%(setup not fully disclosed)
GPQA Diamondaccuracy	91.7%(setup not fully disclosed)
Toolathlon Verifiedpass_rate	73.5%(setup not fully disclosed)