Gemini-3-Pro API pricing

5 providers serve Gemini-3-Pro. Gemini-3-Pro is a proprietary API model, up to 1049K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-08-15 · list prices from provider APIs
Input floor $2.00/1M at Google Vertex AI, Google Gemini API, GMI Cloud and 2 more Output floor $12.00/1M at Google Vertex AI, Google Gemini API, GMI Cloud and 2 more Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Google Vertex AI $2.00 $12.00output floor $0.200 1049K Use
Google Gemini API $2.00 $12.00 $0.200 1049K Use
GMI Cloud $2.00 $12.00 - 1049K Use
OpenRouter $2.00 $12.00 $0.200 1049K Use
Replicate $2.00 $12.00 - - Use

The cheapest way to run Gemini-3-Pro

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $500/month — the same at Google Vertex AI, Google Gemini API, GMI Cloud and 2 more. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Gemini 2.5 Flash $0.150 $0.600 8
Gemini 2.5 Pro $1.25 $10.00 7
Gemini-2.0-Flash-001 $0.100 $0.400 4
Gemini 2.5 Flash Lite $0.075 $0.300 4
Gemini 3 Flash Preview $0.500 $3.00 4
Gemini-2.0-Flash $0.100 $0.400 3

FAQ

What is the cheapest API for Gemini-3-Pro?

As of 2026-08-15, the lowest input price for Gemini-3-Pro, $2.00 per 1M tokens, is the same list price at Google Vertex AI, Google Gemini API, GMI Cloud and 2 more. The lowest output price, $12.00 per 1M tokens, is likewise shared by the same providers. The cheapest provider for a real workload depends on its input/output mix.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON