Google: Gemini 3.8 Flashgoogle
Bottom Line
Google: Gemini 3.8 Flash: $0.82/1M input, $4.13/1M output, 1.0M context, CPS grade A. Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
API Pricing (per 1M tokens)
| Input | $0.82 |
| Output | $4.13 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.65 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 66K |
| Intelligence | 41 |
| Coding | 76 |
| Math | — |
| Speed | 127 tok/s |
| TTFT | 16.15s |
| CPS Grade | A |
| Input / Output Modalities | text, image, video, file, audio → text |
More from google
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Google: Gemini 3.8 Flash API cost?
Google: Gemini 3.8 Flash costs $0.82/1M input tokens and $4.13/1M output tokens. Blended cost at a 3:1 ratio is about $1.65/1M tokens.
What is the context window of Google: Gemini 3.8 Flash?
Google: Gemini 3.8 Flash supports a 1.0M token context window with up to 66K output tokens.
Is Google: Gemini 3.8 Flash worth it?
Google: Gemini 3.8 Flash has a CPS grade of A (score 71), intelligence index 41, coding index 76. Use the compare page to benchmark against rivals.