# Controlling bos, eos, etc in api-inference
**URL:**
**Author:**  [@cristivlad](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fcristivlad)%5C
**Post date:** [April 22, 2021, 7:59pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcontrolling-bos-eos-etc-in-api-inference%2F5701%2F1 "2021-04-22T19:59:26Z")
Is there a way to control the beginning of sentence, end of sentence tokens through the inference api? I could not find it in the documentation.
---
**Author:**  [@Narsil](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FNarsil)%5C
**Post date:** [May 4, 2021, 3:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcontrolling-bos-eos-etc-in-api-inference%2F5701%2F2 "2021-05-04T15:18:19Z")
Hi @cristivlad ,
Currently there is no way to override those within the API.
We are adding and `end_sequence` parameter to enable stopping the generation when using prompt-like generation (for GPT-Neo for instance).
For BOS, what did you want to do with it ?
Cheers,
Nicolas
---
**Author:**  [@louis030195](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flouis030195)%5C
**Post date:** [January 12, 2022, 8:33pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcontrolling-bos-eos-etc-in-api-inference%2F5701%2F3 "2022-01-12T20:33:13Z")
I tried **end\_sequence** and indeed works, I would suggest updating the [doc](/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fdocs%2Fpython%2Fhtml%2Fdetailed_parameters.html%23text-generation-task)%2C thanks in any case! 🙂
```python
data = json.dumps(
{
"inputs": "1+1=2\n2+2=",
"parameters": {
"max_length": 50,
"num_return_sequences": 1,
"return_text": False,
"return_full_text": False,
"do_sample": True,
"top_k": 50,
"top_p": 0.95,
"end_sequence": "\n"
},
"options": {
"wait_for_model": True,
},
}
)
```