# Gemini 3.5 Flash Thinking API prices

Gemini 3.5 Flash Thinking (gemini-flash) — 1.0M context, 66k max output.
2 metered per-token offers from 2 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $1.5 | $9 | — | 1.0M |
| NanoGPT | $1.5 | $9 | $0.15 | 1.0M |

## Summary

- Cheapest input: $1.5 per 1M tokens (302.AI)
- Cheapest output: $9 per 1M tokens (302.AI)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-05-19
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.5 Flash Thinking API?

As of Oct 4, 2026, 302.AI has the lowest Gemini 3.5 Flash Thinking output price at $9 per 1M tokens, and 302.AI has the lowest input price at $1.5 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Gemini 3.5 Flash Thinking?

2 providers list Gemini 3.5 Flash Thinking on Sovyron; 2 of them sell it at a metered per-token price.

### Is Gemini 3.5 Flash Thinking free?

No provider in the Sovyron catalog lists a free tier for Gemini 3.5 Flash Thinking.

### What is the context window of Gemini 3.5 Flash Thinking?

Gemini 3.5 Flash Thinking supports a 1.0M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-3-5-flash-thinking/
Full dataset: https://sovyron.com/data/catalog.json