---
title: "Gemini API pricing"
canonical: https://relayswitch.io/pricing/gemini
generated: 2026-10-27T11:10:06.633Z
source: https://api.relayswitch.io/v1/catalog
base_url: https://api.relayswitch.io/v1
---

Checked 2026-10-26

# Gemini API pricing

Gemini input, cached-input and output prices on one key, read live from the catalog. Prepaid by card or crypto, no KYC, no subscription.

A Flash model for volume and latency, a Pro or Argon model for long, hard reasoning. The million-token context is on most of the line, so the choice is about price per answer, not about what fits. Every row below is a live catalog read; prices are USD per million tokens and the developer list appears where recorded.

## 01Every Gemini model

| Model | Input | Cached | Output | Developer list in / out | Context |
| --- | --- | --- | --- | --- | --- |
| [Gemini 4 Argon](https://relayswitch.io/models/gemini-4-argon) | $0.60 (70% under) | $0.06 | $3.00 (70% under) | $2.00 / $10.00 | 1M tokens |
| [Gemini 3.8 Flash](https://relayswitch.io/models/gemini-3.8-flash) | $0.4925 (34% under) | $0.0493 | $2.25 (40% under) | $0.75 / $3.75 | 1M tokens |
| [Gemini 3.7 Flash](https://relayswitch.io/models/gemini-3.7-flash) | $0.4925 (34% under) | $0.0493 | $2.25 (39% under) | $0.75 / $3.75 | 1M tokens |
| [Gemini 3.5 Flash Lite](https://relayswitch.io/models/gemini-3.5-flash-lite) | $0.225 (25% under) | $0.0225 | $1.875 (25% under) | $0.30 / $2.50 | 1M tokens |
| [Gemini 3.6 Flash](https://relayswitch.io/models/gemini-3.6-flash) | $0.4925 (34% under) | $0.0492 | $2.25 (39% under) | $0.75 / $3.75 | 1M tokens |
| [Gemini 3.5 Flash](https://relayswitch.io/models/gemini-3.5-flash) | $1.50 | $0.15 | $9.00 | $1.50 / $9.00 | 1M tokens |
| [Gemini 3.5 Flash High](https://relayswitch.io/models/gemini-3.5-flash-high) | $0.6353 (57% under) | $0.0635 | $3.8118 (57% under) | $1.50 / $9.00 | 1M tokens |
| [Gemini 3.5 Flash LOW](https://relayswitch.io/models/gemini-3.5-flash-low) | $1.00 (33% under) | $0.10 | $6.375 (29% under) | $1.50 / $9.00 | 1M tokens |
| [Gemini 3.1 Flash Lite Preview](https://relayswitch.io/models/gemini-3.1-flash-lite-preview) | $0.1875 (25% under) | $0.0188 | $1.125 (25% under) | $0.25 / $1.50 | 1M tokens |
| [Gemini 3.1 Pro Preview](https://relayswitch.io/models/gemini-3.1-pro-preview) | $1.20 (40% under) | $0.12 | $7.20 (40% under) | $2.00 / $12.00 | 1M tokens |
| [Gemini 3 Flash Preview](https://relayswitch.io/models/gemini-3-flash-preview) | $0.375 (25% under) | $0.0375 | $2.25 (25% under) | $0.50 / $3.00 | 1M tokens |
| [Gemini 2.5 Flash](https://relayswitch.io/models/gemini-2.5-flash) | $0.09 (70% under) | $0.009 | $0.75 (70% under) | $0.30 / $2.50 | 1M tokens |
| [Gemini 2.5 Pro](https://relayswitch.io/models/gemini-2.5-pro) | $0.9375 (25% under) | $0.0938 | $7.50 (25% under) | $1.25 / $10.00 | 1M tokens |
| [Gemini 2.5 Flash Lite](https://relayswitch.io/models/gemini-2.5-flash-lite) | $0.075 (25% under) | $0.06 | $0.30 (25% under) | $0.10 / $0.40 | — |
| [Gemini 3.1 Flash Lite](https://relayswitch.io/models/gemini-3.1-flash-lite) | $0.15 (40% under) | $0.15 | $0.90 (40% under) | $0.25 / $1.50 | — |
| [Gemini 3.1 Flash Image](https://relayswitch.io/models/gemini-3.1-flash-image) | $13.192 | $13.192 | $1,583.04 | — | — |
| [Gemini 3.1 PRO Preview Customtools](https://relayswitch.io/models/gemini-3.1-pro-preview-customtools) | $4.80 | $0.48 | $28.80 | — | 1M tokens |
| [Gemini Flash Latest](https://relayswitch.io/models/gemini-flash-latest) | $1.80 | $0.18 | $9.00 | — | 1M tokens |
| [Gemini Flash Lite Latest](https://relayswitch.io/models/gemini-flash-lite-latest) | $0.72 | $0.072 | $6.00 | — | 1M tokens |
| [Gemini PRO Latest](https://relayswitch.io/models/gemini-pro-latest) | $4.80 | $0.48 | $28.80 | — | 1M tokens |

USD per million tokens, read from the RelaySwitch catalog when this page was built. Developer list: the catalog's record of the developer's own price.

## 02Which model should I use?

A Flash model for volume and latency, a Pro or Argon model for long, hard reasoning. The million-token context is on most of the line, so the choice is about price per answer, not about what fits. Compare the worked models below before choosing for production.

## 03Worked models

-   [Gemini 4 Argon](https://relayswitch.io/models/gemini-4-argon) — 0.6000 input / 3.0000 output per million tokens.
-   [Gemini 3.1 Pro Preview](https://relayswitch.io/models/gemini-3.1-pro-preview) — 1.2000 input / 7.2000 output per million tokens.
-   [Gemini 3.8 Flash](https://relayswitch.io/models/gemini-3.8-flash) — 0.4925 input / 2.2500 output per million tokens.

## Questions

Is Gemini billed monthly?

No. Credit is prepaid and each request bills per token.

Can I pay for Gemini with crypto?

Yes: USDT, USDC, BTC, ETH or SOL, alongside card, Apple Pay and PayPal.