Models / Qwen
Qwen3.8 Omni Flash
by Qwen ·
qwen/qwen3.8-omni-flashQwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...
reasoningtool-usevisionreleased 2026-09-21
Legal score · raw
-
not yet benchmarked
Context
1M
max output 131K
Input
$0.19
per 1M tokens
Output
$0.59
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.02
9.4x cheaper than uncached
Uncached input
$0.19
per 1M tokens
Capabilities
Modalities
in textimageaudiovideo
out text
Request parameters it accepts
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.