Seconding that I am experiencing this issue. Seeing responses with both 2.5 flash and 2.5 pro sometimes halt in the middle of a sentence at random. This is with context and tokens that are well below the limits (<50k input tokens, <500 output tokens) and with or without structured outputs.
jmccain
17
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Truncated responses despite being under limits | 2 | 1307 | June 11, 2025 | |
| Gemini 3 output limited to ~4k tokens instead of 65k | 9 | 1570 | January 14, 2026 | |
| Gemini 2.0 thinking model returning truncated response with a blob of whitespace | 6 | 1253 | January 25, 2025 | |
| `max_output_tokens` isn't respected when using `gemini-2.5-flash` model | 7 | 1178 | October 4, 2025 | |
| Gemini 2.5 API bug: missing finishReason when max token limit is reached | 1 | 1129 | April 30, 2025 |