Gemini 3 Flash Preview

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

$1.13Blended $/1M (3:1)

$0.5Input $/1M

$3Output $/1M

$3.501M in + 1M out

$0.05 −90%Cache read $/1M

#3318 of 5,000Cheapest rank

Provider: ZenMux (zenmux)
Context: 1,048,000 tokens
Max output: 64,000 tokens
Capabilities: toolsreasoningtextimagepdfaudio

Same model, other providers

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

Provider	Input	Output	Blended	Context
QiHang	$0.07	$0.43	$0.16	1049k
ZenMux (this)	$0.5	$3	$1.13	1048k
CrossModel	$0.5	$3	$1.13	1049k
Google	$0.5	$3	$1.13	1049k
LLM Gateway	$0.5	$3	$1.13	1049k
Neon	$0.5	$3	$1.13	1049k
FrogBot	$0.5	$3	$1.13	1049k
Pioneer	$0.5	$3	$1.13	1049k
Abacus	$0.5	$3	$1.13	1049k

Call it

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

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

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