Long context

Gemini 3 Flash Preview API pricing

Google's Gemini series — very long context windows and strong multimodal input.

Model IDgoogle/gemini-3-flash-preview

ChatStreamingTool callingVision

Get API Key Run your first request

Call summary

Input

$1.7143$1.20/ 1M tokens

Cache write $1.20

Cache read $1.20

Output

$11.4286$8.00/ 1M tokens

Context Window

1.05M

API Endpoints

Gemini 3 Flash Preview API endpoints

One API key — this model is served on the endpoint below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Chat Completions reference

Call Gemini 3 Flash Preview from your code

Your API key works on this endpoint.

Endpoint

/v1/chat/completions

Model ID

google/gemini-3-flash-preview

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "google/gemini-3-flash-preview",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Successful response share

100.00%

Success 2xx

100.00%

Rate limit 429

0.00%

Server 5xx

0.00%

TPS

267.18

tokens/s

Avg. time to first token

3.16 s

Avg. latency

5.36 s

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

Updated Oct 26, 2026, 2:12 AM UTC

More Gemini models on Router One

20 other Gemini models on the same gateway and API key — each page lists endpoints, posted price, and context window.

8 channel versions

Gemini 3 Flash Preview at a glance

Gemini 3 Flash Preview (model ID google/gemini-3-flash-preview) is a Gemini-series text model on Router One. google/gemini-3-flash-preview is the catalog id with the -preview suffix; google/gemini-3-flash is listed separately at its own rate. Posted rate: $1.20 in / $8.00 out per 1M tokens (was $1.7143 in / $11.4286 out). Router One subscriptions include Gemini 3 Flash Preview in the Standard models allowance: Pro 5,000, Max 8,000, Ultra 25,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 256,000 / 512,000 input tokens counts as 2 / 4 requests. Context window: 1.05M tokens. Accepts text, image; returns text. Endpoint: POST /v1/chat/completions (OpenAI-compatible).

Gemini 3 Flash Preview FAQ

How much does Gemini 3 Flash Preview cost on Router One?

Gemini 3 Flash Preview is billed per token on Router One: $1.20 in / $8.00 out per 1M tokens, pay as you go.

Is Gemini 3 Flash Preview included in Router One subscriptions?

Router One subscriptions include Gemini 3 Flash Preview in the Standard models allowance: Pro 5,000, Max 8,000, Ultra 25,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 256,000 / 512,000 input tokens counts as 2 / 4 requests.

Which endpoints serve Gemini 3 Flash Preview?

Gemini 3 Flash Preview is served on POST /v1/chat/completions (OpenAI-compatible). Any Router One API key works there.

What is Gemini 3 Flash Preview's context window?

Gemini 3 Flash Preview accepts up to 1.05M tokens of context per request on Router One.

Start using Gemini 3 Flash Preview

Create an API key and call Gemini 3 Flash Preview at $1.20 in / $8.00 out per 1M tokens on Router One — pay as you go, with per-request cost and latency visibility.

Get API Key Plans & pay-as-you-go pricing Compare models side by side Quickstart guide Gemini API in China