> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt.
> For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# How to control where the model stops using `stop`

> Tell the model to **stop generating further tokens.

The `stop` parameter lets you define **one or more strings** that tell the model to **stop generating further tokens** when it encounters them.

* The stop sequence(s) will **not appear** in the returned text.
* `stop` is a **hard stop**: the model will not generate anything past the stop string.
* You can use `stop` to:
  * **Format structured outputs**
  * Avoid responses that **run too long**
  * Segment **multi-part answers**

### How it works:

* You can pass:
  * A single **string**
  * Or a **list of up to 4 strings**
* The model will stop generating as soon as **any stop string is matched**.

---

### Parameter details:

| Parameter | Type                      | Limits      |
| --------- | ------------------------- | ----------- |
| `stop`    | String or List of Strings | Max 4 items |

---

### When to use `stop`:

| Scenario                          | Example `stop`              |
| --------------------------------- | --------------------------- |
| Building chat with system markers | `"###"`                     |
| Multi-turn Q\&A                   | `"\nQ:"`                    |
| Ending output before next prompt  | `"User:"`                   |
| Preventing overly long answers    | `["###", "\nUser:", "End"]` |

First, install the SDK:

```bash
pip install -Uqq sarvamai
```

Then use the following Python code:

```python
from sarvamai import SarvamAI

# Initialize the SarvamAI client with your API key
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")

# Example 1: Using single stop string
response = client.chat.completions(
    model="sarvam-105b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant. End your answers with ###."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
    stop="###"  # Stop when "###" is reached
)

# Receive assistant's reply as output
print(response.choices[0].message.content)
```

```python
from sarvamai import SarvamAI

client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")

# Example 2: Using list of stop strings
response = client.chat.completions(
    model="sarvam-105b",
    messages=[
        {"role": "system", "content": "You are an expert answering user questions."},
        {"role": "user", "content": "Explain what a black hole is."}
    ],
    stop=["###", "\nUser:", "\nQ:"]  # Multiple stop sequences
)

# Receive assistant's reply as output
print(response.choices[0].message.content)
```

> Tell the model to **stop generating further tokens.