Gemini 3.8 Flash API
Gemini 3.8 Flash adds stronger coding, multi-step reasoning and tool use to Google's fast Flash line of models.
Prices are temporarily unavailable — refresh the page in a minute.
What Gemini 3.8 Flash is good for
Gemini 3.8 Flash is Google's Flash-family model tuned for long coding tasks, agent workflows and multi-step reasoning, while keeping the speed the Flash line is built around. It can call tools again and again, judge what came back and keep working toward a goal, and its reasoning effort can be raised or lowered per task. It suits coding agents, research assistants and finance or legal analysis.
- Coding agents that plan, write and debug across long tasks
- Research loops where the model calls tools, checks results and refines
- Finance, legal and STEM questions that need careful step-by-step reasoning
- Fast first drafts of scripts, outlines and summaries in bulk
Gemini 3.8 Flash pricing
| Option | Price, USD | Video Blade tokens |
|---|---|---|
| Input | tokens | |
| Output | tokens |
Prices are per 1M text tokens (about 750,000 words of model text) and live from our price list. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing.
Gemini 3.8 Flash is coming soon to Video Blade
It is listed with its live price so you can compare it. You can't order it through Video Blade yet.
Gemini 3.8 Flash FAQ
How much does Gemini 3.8 Flash cost?
1M text tokens from . Prices are live from our price list, and you see the exact price before anything runs.
Is Gemini 3.8 Flash better than Gemini 3.7 Flash?
In published benchmarks it beats 3.7 Flash on coding, reasoning and agent tasks, posting 73.7% on DeepSWE v1.1 and 54.9% on HLE-Verified. The trade-off is that it can think longer on hard problems, which is why Google keeps 3.7 Flash available for workloads where efficiency comes first.
What is Gemini 3.8 Flash Cyber?
A separate version of Gemini 3.8 Flash built for security work, such as finding vulnerabilities and writing patches automatically. Google offers it only to trusted security teams through its Fairwind Program, while the standard Gemini 3.8 Flash remains the general-purpose choice for coding, reasoning and agent tasks.
Can I use Gemini 3.8 Flash on Video Blade today?
Not yet. Gemini 3.8 Flash is listed with its live price so you can compare it with the models you can use today; ordering it through Video Blade is coming soon.
How is Gemini 3.8 Flash billed?
Per million text tokens of the model, with separate rates for the text you send and the text you get back. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing. Current prices are shown on this page.
Gemini 3.8 Flash in the Video Blade API
gemini-gemini-3-8-flashOrdering this model through the API is coming soon.