// gemini
Gemini 3.1 Pro
Google’s flagship. 1M context, native multimodal.
Temporarily unavailable
Our upstream lists gemini-3.1-pro-preview but is not currently serving it, so
calls fail rather than bill. Upstream capacity moves around week to week and this one may well come
back — we would rather show you the gap than take a signup for it today.
For work you can run today, Gemini 3.5 Flash is live at
$0.75/M input.
Official list
llmrelay
Input / M tokens
$2.00
$1.00
Output / M tokens
$12.00
$6.00
Context window
—
1,048,576 tokens
Max output
—
65,536 tokens
What it costs you per month
Real-world budget scenarios. Numbers are simple sums — official list price vs llmrelay's 50% off tier.
Usage scenario
Official
llmrelay
Light coding (1M in / 200K out per month)
$4.40
$2.20save $2.20
Heavy Cursor / Cline user (50M in / 5M out per month)
$160.00
$80.00save $80.00
Production RAG (500M in / 20M out per month)
$1240.00
$620.00save $620.00
What it's good at
- +1M token context
- +Native video / image input
- +Strong long-context recall
Best for
- — Video summarization
- — Massive-context reasoning
- — Multimodal RAG
Run Gemini 3.5 Flash instead
Gemini 3.1 Pro is not callable on llmrelay today, so we are not going to sell you an API key for it. Gemini 3.5 Flash is live at $0.75/M input, also 50% off list.
View Gemini 3.5 Flash →