# Output truncated without reason
**URL:** https://discuss.vllm.ai/t/output-truncated-without-reason/1237
**Category:** General
**Created:** [July 30, 2025, 7:26am UTC](https://discuss.vllm.ai/t/output-truncated-without-reason/1237 "2025-07-30T07:26:46Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@shaojun0](https://discuss.vllm.ai/u/shaojun0)
#### Post date: [July 30, 2025, 7:26am UTC](https://discuss.vllm.ai/t/output-truncated-without-reason/1237/1 "2025-07-30T07:26:46Z")
### system info
| key | value |
| --- | --- |
| transformers version | 4.51.3 |
| PyTorch version | 2.6.0 |
| vllm version | 0.8.0 |
| GPU | 4090\*1 |
### Reproduction
I tried running this model, but the output was always staged and displayed as a length stage, but there was no problem with the configuration.
### config
```sh
python3 -m vllm.entrypoints.openai.api_server --max_model_len 4096 --served-model-name seed-x --model /data/models/Seed-X-PPO-7B
```
### request json
```json
{
"model": "seed-x",
"max_token":4096,
"prompt": "Translate the following English sentence into Chinese:\nThe image captures a charming scene featuring a small grey mouse with a white belly. The mouse is perched on a blue surface, which could be a table or a piece of furniture. It's engaged in the delightful activity of nibbling on a vibrant red strawberry, which appears juicy and ripe. The mouse's attention is fully absorbed by its sweet treat, suggesting it's enjoying its meal. The background is blurred but hints at a room with white walls, possibly indicating an indoor setting. The overall scene exudes a sense of tranquility and simplicity."
}
```
---
### Author:  [@RunLLM](https://discuss.vllm.ai/u/RunLLM)
#### Post date: [July 30, 2025, 7:27am UTC](https://discuss.vllm.ai/t/output-truncated-without-reason/1237/2 "2025-07-30T07:27:15Z")
Your output is being truncated due to the `max_token` parameter (should be `max_tokens`) and possibly the model’s maximum context length. The correct parameter for vLLM’s OpenAI-compatible API is `max_tokens`, not `max_token`. Also, the sum of input and output tokens must not exceed the model’s `max_model_len` (4096 in your config). If the prompt is long, the model may stop early with `finish_reason: "length"` even if you set a high `max_tokens` value. See [this issue](https://github.com/vllm-project/vllm/issues/1525) and [this issue](https://github.com/vllm-project/vllm/issues/19861) for details.
To fix, use `"max_tokens"` in your request, and ensure your prompt plus `max_tokens` does not exceed 4096 tokens. If you still see truncation, try reducing prompt length or increasing `max_model_len` if your GPU has enough memory. Would you like a step-by-step example or more troubleshooting tips?
Sources:
- [Output response is truncated](https://github.com/vllm-project/vllm/issues/1525)
- [max\_completion\_tokens doesn’t work as max](https://github.com/vllm-project/vllm/issues/19861)
---
### Author:  [@shaojun0](https://discuss.vllm.ai/u/shaojun0)
#### Post date: [July 30, 2025, 7:37am UTC](https://discuss.vllm.ai/t/output-truncated-without-reason/1237/3 "2025-07-30T07:37:40Z")
Thank you very much…….