---
title: "Gemini 3.5 Flash — API access"
description: "Gemini 3.5 Flash API pricing: official $1.50/$9.00 per 1M tokens, $0.75/$4.50 with the flat 50% apiToken.sale discount. Proven Flash tier on the native Google API."
url: "https://apitoken.sale/models/gemini-3-5-flash"
language: "en"
---
# Gemini 3.5 Flash

Gemini 3.5 Flash is the previous-generation Flash — a proven high-throughput model for coding and multimodal workloads, at the same input rate as 3.6 Flash.

- **Model ID:** `gemini-3.5-flash`
- **Tier:** Flash
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $1.5 input / $9 output
- **Your price (per 1M):** input $0.75, output $4.5 (flat 50% off)
- **Base URL:** `https://gemini.api.apitoken.sale` · **Endpoint:** `POST /v1beta/models/gemini-3.5-flash:generateContent` (x-goog-api-key)

## Best for

- Workloads pinned to Gemini 3.5 Flash for reproducibility.
- High-volume production API traffic.
- Multimodal pipelines migrating gradually to 3.6 Flash.

## Notes

- Same input price as Gemini 3.6 Flash, but output is $9.00 vs $7.50 — new work should default to gemini-3.6-flash.
- Cached input bills at 10% of input; caching is automatic on repeated prefixes.

## Call it

```bash
curl https://gemini.api.apitoken.sale/v1beta/models/gemini-3.5-flash: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 3.5 Flash API cost?**

Officially $1.50 per 1M input tokens and $9.00 per 1M output tokens, with cached input at $0.15. With the flat 50% apiToken.sale discount that is $0.75/$4.50.

**Gemini 3.5 Flash or 3.6 Flash?**

They share an input price, and 3.6 Flash is newer with cheaper output ($7.50 vs $9.00) — prefer it for new projects. Stay on 3.5 Flash when your prompts and evals are pinned to it.

**What is the model ID?**

gemini-3.5-flash. It works on the same apiToken.sale key and balance as every other Claude, GPT and Gemini model — send it as the model on the native Gemini endpoint with x-goog-api-key.

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