Models / Google
Gemini 3 Flash Preview
by Google ·
google/gemini-3-flash-previewGemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
reasoningtool-usevisionreleased 2025-12-17
Legal score · raw
-
not yet benchmarked
Context
1.05M
max output 66K
Input
$0.63
per 1M tokens
Output
$3.75
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
$0.06
10x cheaper than uncached
Cache write
$0.10
per 1M tokens, charged once
Uncached input
$0.63
per 1M tokens
Capabilities
Modalities
in textimagefileaudiovideo
out text
Request parameters it accepts
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_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.