Gemini 3 Pro Preview

qihang-ai/gemini-3-pro-preview · family gemini-pro · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimageaudiovideo.

$1.29Blended $/1M (3:1)

$0.57Input $/1M

$3.43Output $/1M

$4.001M in + 1M out

—Cache read $/1M

#3460 of 5,000Cheapest rank

Provider: QiHang (qihang-ai)
Context: 1,000,000 tokens
Max output: 65,000 tokens
Capabilities: toolsreasoningtextimageaudiovideo

Same model, other providers

“Gemini 3 Pro Preview” is offered by 4 providers — cheapest-effective first. This one (QiHang) is the cheapest.

Provider	Input	Output	Blended	Context
QiHang (this)	$0.57	$3.43	$1.29	1000k
Merge Gateway	$2	$12	$4.50	1049k
Databricks	$2	$12	$4.50	1049k
NEAR AI Cloud	$1.25	$15	$4.69	1049k

Call it

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

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