jishie

Gemini 3.6 Flash

venice/gemini-3-6-flash · family gemini-flash · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimageaudiovideo.

$3.75Blended $/1M (3:1)
$1.875Input $/1M
$9.375Output $/1M
$11.251M in + 1M out
$0.1875 −90%Cache read $/1M
#4632 of 5,000Cheapest rank
Provider
Venice AI (venice)
Context
1,000,000 tokens
Max output
65,536 tokens
Capabilities
toolsreasoningtextimageaudiovideo

Same model, other providers

“Gemini 3.6 Flash” is offered by 9 providers — cheapest-effective first. Requesty is the cheapest at $2.88 blended.

ProviderInputOutputBlendedContext
Requesty$1.5$7$2.881049k
Impossibl$1.5$7.5$3.001049k
CrossModel$1.5$7.5$3.001049k
Google$1.5$7.5$3.001049k
NanoGPT$1.5$7.5$3.001049k
LLM Gateway$1.5$7.5$3.001049k
OpenCode Zen$1.5$7.5$3.001049k
GitHub Copilot$1.5$7.5$3.001000k
Venice AI (this)$1.875$9.375$3.751000k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Venice 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-3-6-flash","messages":[{"role":"user","content":"hello"}]}'

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