jishie

Gemini 3.1 Flash Lite

302ai/gemini-3.1-flash-lite · family gemini-flash-lite · in: text, image, video, audio, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video audio pdf.

$0.56
Blended $/1M (3:1)
$0.25
Input $/1M
$1.5
Output $/1M
$1.75
1M in + 1M out
Cache read $/1M
#2847 of 7,094
Cheapest rank
Provider
302.AI (302ai)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text image video audio pdf

Same model, other providers

“Gemini 3.1 Flash Lite” is offered by 20 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.001M
Kilo Gateway$0.125$0.75$0.281M
302.AI (this)$0.25$1.5$0.561M
NanoGPT$0.25$1.5$0.561M
Impossibl$0.25$1.5$0.561M
AIHubMix$0.25$1.5$0.561M
OrcaRouter$0.25$1.5$0.561M
Vertex$0.25$1.5$0.561M
Pioneer$0.25$1.5$0.561M
Requesty$0.25$1.5$0.561M
Google$0.25$1.5$0.561M
Vercel AI Gateway$0.25$1.5$0.561M
DevPass (LLM Gateway)$0.25$1.5$0.561M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at 302.AI and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemini-3.1-flash-lite","messages":[{"role":"user","content":"hello"}]}'

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

← all 302.AI models · model index · JSON