jishie

Gemini 3.8 Flash

vivgrid/gemini-3.8-flash · family gemini-flash · in: text, image, video, audio, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video audio pdf.

$1.50
Blended $/1M (3:1)
$0.75
Input $/1M
$3.75
Output $/1M
$4.50
1M in + 1M out
$0.15 −80%
Cache read $/1M
#4651 of 7,708
Cheapest rank
Provider
Vivgrid (vivgrid)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
128,000 tokens
Capabilities
tools reasoning text image video audio pdf

Same model, other providers

“Gemini 3.8 Flash” is offered by 21 providers — cheapest-effective first. This one (Vivgrid) is the cheapest.

ProviderInputOutputBlendedContext
Vivgrid (this)$0.75$3.75$1.501M
NanoGPT$0.75$3.75$1.501M
Kilo Gateway$0.75$3.75$1.501M
302.AI$0.75$3.75$1.501M
OpenRouter$0.75$3.75$1.501M
Google$0.75$3.75$1.501M
Vercel AI Gateway$0.75$3.75$1.501M
Ofox$0.75$3.75$1.501M
AIHubMix$0.75$3.75$1.501M
Merge Gateway$0.75$3.75$1.501M
GitHub Copilot$0.75$3.75$1.501M
Eden AI$0.75$3.75$1.501M
Tempr$0.75$3.75$1.501M

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemini-3.8-flash","messages":[{"role":"user","content":"hello"}]}'

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

← all Vivgrid models · model index · JSON