Input
- Official Google
- $1.5
- Here (−50%)
- $0.75
gemini-3.5-flash
Gemini 3.5 Flash API — price per token
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.
Pricing per 1M tokens
| Rate | Official Google | Here (−50%) |
|---|---|---|
| Input | $1.5 | $0.75 |
| Cached input | $0.15 | $0.075 |
| Output | $9 | $4.5 |
Cached input
- Official Google
- $0.15
- Here (−50%)
- $0.075
Output
- Official Google
- $9
- Here (−50%)
- $4.5
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 1M tokens. Max output: 64K tokens.
Best for
- Workloads pinned to Gemini 3.5 Flash for reproducibility.
- High-volume production API traffic.
- Multimodal pipelines migrating gradually to 3.6 Flash.
Good to know
- 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.
How to use Gemini 3.5 Flash
Create a free account, generate one key, and point any Gemini-compatible tool at https://gemini.api.apitoken.sale with model ID gemini-3.5-flash — the native /v1beta/models/gemini-3.5-flash:generateContent surface works, authenticated with x-goog-api-key. New accounts include $10 of API usage at official prices — enough to test the model before topping up.
Frequently asked questions
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.
Run Gemini 3.5 Flash on the native Gemini API at a flat 50% off — instant key, prepaid balance, card or crypto.