Gemini 3.6 Flash (batch)
Google · Multimodal · Released Jul 2026
Gemini 3.6 Flash (batch) is Google's text-only model optimized for batch processing with a 1M token context window, positioned between the lightweight 3.5 Flash Lite and the multimodal 3.7 Flash models.
- Strengths
- Handles large text workloads efficiently in batch mode with a full 1M token context window for long-document processing.
- Best for
- Batch jobs processing large volumes of text-only data where latency is not a constraint.
- Limitations
- Text-only and optimized for batch workflows, so unsuitable for real-time inference or applications requiring multimodal inputs like images or video.
Input / 1M
$0.375
Output / 1M
$1.88
Cached input / 1M
$0.0375
Context window
1.05M
Also billed
- Cache write
- $0.0417 / 1M
- Audio input
- $0.375 / 1M
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 50.0% out decreased 50.0%
- 90d
- in decreased 50.0% out decreased 50.0%
- 1y
- in decreased 50.0% out decreased 50.0%
- Since launch
- in decreased 50.0% out decreased 50.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 13 Aug 2026 | $0.375 | $1.88 | $0.0375 | Imported from OpenRouter | openrouter.ai |
| 28 Jul 2026 | $0.75 | $3.75 | $0.075 | Imported from OpenRouter | openrouter.ai |