Gemini 3.8 Flash
Google · Multimodal · Released Sep 2026
Gemini 3.8 Flash is Google's latest multimodal Flash model with a 1M token context window, supporting text, image, video, and audio inputs.
- Strengths
- Delivers improved performance on software engineering, agentic tasks, and multi-step reasoning compared to earlier Flash variants.
- Best for
- Fast inference workloads requiring stronger reasoning and coding capability, particularly multi-turn agentic applications and software development tasks.
- Limitations
- A newer generation step up from Gemini 3.7 Flash, so substantially more capable but likely at higher inference cost per token than prior Flash models.
Input / 1M
$0.75
Output / 1M
$3.75
Cached input / 1M
$0.075
Context window
1.05M
Also billed
- Cache write
- $0.0417 / 1M
- Audio input
- $0.75 / 1M
- Image input
- $0.000001 / image
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 2 Sep 2026 | $0.75 | $3.75 | $0.075 | Imported from OpenRouter | openrouter.ai |