Gemini 3.5 Flash Lite (batch)
Google · Multimodal · Released Jul 2026
Gemini 3.5 Flash Lite (batch) is Google's lightweight text-only model optimized for batch processing with a 1M token context window.
- Strengths
- It delivers fast inference and lower latency than standard Flash models, making it suitable for time-sensitive or high-volume text workloads.
- Best for
- Batch processing jobs that prioritize speed and efficiency over multimodal capabilities, such as large-scale text summarization, classification, or data extraction.
- Limitations
- Text-only model with no support for image, video, or audio inputs; suitable only for batch processing, not real-time streaming applications.
Input / 1M
$0.15
Output / 1M
$1.25
Cached input / 1M
$0.015
Context window
1.05M
Also billed
- Audio input
- $0.15 / 1M
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 28 Jul 2026 | $0.15 | $1.25 | $0.015 | Imported from OpenRouter | openrouter.ai |