Gemini 2.5 Flash Limits
Token limits
| Spec | Value |
|---|---|
| Context window | 1,048,576 input tokens |
| Max output | 65,536 tokens |
| Input types | Text, Image, Video, Audio |
| Output types | Text |
Rate limits
Batch API limit on tokens waiting in the queue.
| Limit | Tokens |
|---|---|
| Batch enqueued tokens | 3,000,000 |
Source: google.dev, read Nov 9, 2026.
Get an email when we log a change to Gemini 2.5 Flash
Questions
What is the Gemini 2.5 Flash context window
1,048,576 input tokens, per ai.google.dev, read Nov 9, 2026.
What is the Gemini 2.5 Flash max output
65,536 tokens, per ai.google.dev.
What are the Gemini 2.5 Flash rate limits
Batch API limit on tokens waiting in the queue. Tokens 3,000,000 at the Batch enqueued tokens tier, per ai.google.dev.
Source: google.dev, read Nov 9, 2026.