Gemini 3.5 Flash Lite

google-vertex/gemini-3.5-flash-lite · family gemini-flash-lite · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideoaudiopdf.

$0.85Blended $/1M (3:1)

$0.3Input $/1M

$2.5Output $/1M

$2.801M in + 1M out

$0.03 −90%Cache read $/1M

#2958 of 5,000Cheapest rank

Provider: Vertex (google-vertex)
Context: 1,048,576 tokens
Max output: 65,536 tokens
Capabilities: toolsreasoningtextimagevideoaudiopdf

Same model, other providers

“Gemini 3.5 Flash Lite” is offered by 9 providers — cheapest-effective first. This one (Vertex) is the cheapest.

Provider	Input	Output	Blended	Context
Vertex (this)	$0.3	$2.5	$0.85	1049k
Impossibl	$0.3	$2.5	$0.85	1049k
CrossModel	$0.3	$2.5	$0.85	1049k
Google	$0.3	$2.5	$0.85	1049k
NanoGPT	$0.3	$2.5	$0.85	1049k
LLM Gateway	$0.3	$2.5	$0.85	1049k
OpenCode Zen	$0.3	$2.5	$0.85	1049k
Neon	$0.3	$2.5	$0.85	1049k
Pioneer	$0.3	$2.5	$0.85	1000k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Vertex and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemini-3.5-flash-lite","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):