jishie

Gemini 3.8 Flash

opper/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.

$1.65
Blended $/1M (3:1)
$0.825
Input $/1M
$4.13
Output $/1M
$4.95
1M in + 1M out
$0.0825 −90%
Cache read $/1M
#4844 of 7,713
Cheapest rank
Provider
Opper (opper)
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 3.8 Flash” is offered by 21 providers — cheapest-effective first. NanoGPT is the cheapest at $1.50 blended.

ProviderInputOutputBlendedContext
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
Opper (this)$0.825$4.13$1.651M

Call it

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

Most providers are OpenAI-compatible — point base_url at Opper 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 Opper models · model index · JSON