Gemini 2.5 Flash-Lite

kenari/gemini-2-5-flash-lite · family gemini-flash-lite · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimageaudiovideopdf.

freeBlended $/1M (3:1)

freeInput $/1M

freeOutput $/1M

free1M in + 1M out

—Cache read $/1M

#160 of 5,000Cheapest rank

Provider: Kenari (kenari)
Context: 1,048,576 tokens
Max output: 65,536 tokens
Capabilities: toolsreasoningtextimageaudiovideopdf

Same model, other providers

“Gemini 2.5 Flash-Lite” is offered by 9 providers — cheapest-effective first. This one (Kenari) is the cheapest.

Provider	Input	Output	Blended	Context
Kenari (this)	free	free	$0.00	1049k
Impossibl	$0.1	$0.4	$0.18	1049k
CrossModel	$0.1	$0.4	$0.18	1049k
Google	$0.1	$0.4	$0.18	1049k
NEAR AI Cloud	$0.1	$0.4	$0.18	1049k
LLM Gateway	$0.1	$0.4	$0.18	1049k
Ofox	$0.1	$0.4	$0.18	1049k
OrcaRouter	$0.1	$0.4	$0.18	1049k
Vertex	$0.1	$0.4	$0.18	1049k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemini-2-5-flash-lite","messages":[{"role":"user","content":"hello"}]}'

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