---
title: "Gemini 3 Flash Preview — API access"
description: "Gemini 3 Flash Preview API pricing: official $0.50/$3.00 per 1M tokens, $0.25/$1.50 with the flat 50% apiToken.sale discount. Native Gemini access with a 1M-token context window."
url: "https://apitoken.sale/models/gemini-3-flash-preview"
language: "en"
---
# Gemini 3 Flash Preview

Gemini 3 Flash Preview is Google's cost-efficient multimodal Gemini 3 model for agentic coding, tool use and long-context work.

- **Model ID:** `gemini-3-flash-preview`
- **Tier:** Flash
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.5 input / $3 output
- **Your price (per 1M):** input $0.25, output $1.5 (flat 50% off)
- **Base URL:** `https://router.apitoken.sale` · **Endpoint:** `POST /v1beta/models/gemini-3-flash-preview:generateContent` (x-goog-api-key)

## Best for

- Agentic coding and function calling at Flash latency.
- Multimodal text, image, audio and document input.
- Cost-efficient analysis across the full 1M-token window.

## Notes

- Supports minimal, low, medium and high thinking levels on the native Gemini API.
- Text/image/video input is $0.50 per 1M; audio input is $1.00 per 1M. Cached text and audio are $0.05/$0.10 per 1M.

## Call it

```bash
curl https://router.apitoken.sale/v1beta/models/gemini-3-flash-preview:generateContent \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Reply with exactly: connected"}]}]}'
```

## FAQ

**How much does the Gemini 3 Flash Preview API cost?**

Officially $0.50 per 1M text, image or video input tokens and $3 per 1M output tokens, including thinking. Cached text input is $0.05. With the flat 50% apiToken.sale discount that is $0.25/$1.50.

**What is the model ID?**

gemini-3-flash-preview. Use it unchanged with the Google GenAI SDK or another Gemini-compatible client pointed at https://router.apitoken.sale.

**Does it support thinking levels?**

Yes. The native Gemini API accepts minimal, low, medium and high thinking levels for this model.

---
API reference: https://apitoken.sale/md/docs · All models: https://apitoken.sale/md/models