Gemini 3.8 Flash pricing and specs
Gemini 3.8 Flash pricing and specsGoogle's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows
Gemini 3.8 Flash price per 1M tokens
| Type | ₽ / 1M | $ / 1M |
|---|---|---|
| Input tokens | 63,38 ₽ | $0.75 |
| Output tokens | 317 ₽ | $3.75 |
| Cache read | 6,34 ₽ | $0.075 |
Prices in rubles as of 18.09.2026 at the CBR rate: 1 $ = 84.51 ₽.
Gemini 3.8 Flash specs and limits
- Context window
- 1.0M
- Max output
- 66K
- Input
- text, image, video, audio, pdf
- Output
- text
- Family
- gemini-flash
- Released
- 2026-09-02
- Updated
- 2026-09-02
- Also known as
- google gemini 3.8 flash, gemini api 3.8 flash, google ai 3.8 flash, google deepmind 3.8 flash, gemini pro 3.8 flash, gemini flash 3.8 flash
What Gemini 3.8 Flash can do
- ✓Reasoning
- ✓Tool calling
- ✓Structured output
- ✓Attachments / files
- ✓Vision (images)
- ✓Temperature control
- —Open weights
Frequently asked questions
How much does the Gemini 3.8 Flash API cost?
Input costs $0.75 per 1M tokens (63.38 ₽) and output costs $3.75 per 1M (317 ₽). Google bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.
How much do 1,000 Gemini 3.8 Flash tokens cost?
List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.75 for input and $3.75 for output by 1,000. The same rates in rubles are 63.38 ₽ and 317 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.
How many tokens does Gemini 3.8 Flash hold?
The Gemini 3.8 Flash context window is 1.0M tokens (1,048,576). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Google model card as of September 2026.
What are the Gemini 3.8 Flash limits?
The context window is 1.0M tokens (1,048,576) and a single response is capped at 66K tokens, so longer output has to be generated in parts. Rate limits are set by Google per account and depend on your plan rather than on the model, so they are not listed here.
How is the Gemini 3.8 Flash price in rubles calculated?
Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For Gemini 3.8 Flash that gives 63.38 ₽ per 1M input tokens and 317 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.
How is Gemini 3.8 Flash different from other Gemini models?
Gemini 3.8 Flash belongs to the Gemini Flash family at Google. Models in the Gemini line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Gemini model is listed on the provider page.
Can Gemini 3.8 Flash reason?
Yes, Gemini 3.8 Flash declares a reasoning mode: it works through intermediate steps before it answers. Those steps add output tokens, so a call with a long reasoning chain costs more and takes longer than a plain completion. Capabilities declared for the model: reasoning, tool calling, image input, structured output.
What capabilities does Gemini 3.8 Flash support?
The declared capabilities of Gemini 3.8 Flash are: reasoning, tool calling, image input, structured output. It accepts text, images, video, audio, PDF as input, and every attachment consumes tokens from the shared context window of 1.0M tokens. The list comes from the Google model card and is refreshed with the catalog as of September 2026.