jishie

Gemini 3 Flash Preview

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

$1.13Blended $/1M (3:1)
$0.5Input $/1M
$3Output $/1M
$3.501M in + 1M out
$0.05 −90%Cache read $/1M
#3301 of 5,000Cheapest rank
Provider
CrossModel (crossmodel)
Context
1,048,576 tokens
Max output
65,536 tokens
Capabilities
toolsreasoningtextimagevideoaudio

Same model, other providers

“Gemini 3 Flash Preview” is offered by 9 providers — cheapest-effective first. QiHang is the cheapest at $0.16 blended.

ProviderInputOutputBlendedContext
QiHang$0.07$0.43$0.161049k
CrossModel (this)$0.5$3$1.131049k
Google$0.5$3$1.131049k
LLM Gateway$0.5$3$1.131049k
Neon$0.5$3$1.131049k
FrogBot$0.5$3$1.131049k
Pioneer$0.5$3$1.131049k
ZenMux$0.5$3$1.131048k
Abacus$0.5$3$1.131049k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemini/gemini-3-flash-preview","messages":[{"role":"user","content":"hello"}]}'

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