> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bytez.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Get started

> Use the latest AI chat models

<AccordionGroup>
  <Accordion defaultOpen="true" title="Basic usage">
    <CodeGroup>
      ```javascript javascript theme={null}
      import Bytez from 'bytez.js';

      // insert your key
      const sdk = new Bytez('BYTEZ_KEY');

      // choose your model
      const model = sdk.model('Qwen/Qwen3-4B');

      // provide the model with input
      const input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ];

      // send to the model
      const { error, output } = await model.run(input);

      // observe the output
      console.log({ error, output });

      ```

      ```python python theme={null}
      from bytez import Bytez

      # insert your key
      sdk = Bytez("BYTEZ_KEY")

      # choose your model
      model = sdk.model("Qwen/Qwen3-4B")

      # provide the model with input
      input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ]

      # send to the model
      result = model.run(input)

      # observe the output
      print({"error": result.error, "output": result.output})

      ```

      ```bash http theme={null}
      curl -X POST 'https://api.bytez.com/models/v2/Qwen/Qwen3-4B' \
      -H 'Authorization: BYTEZ_KEY' \
      -H 'Content-Type: application/json' \
      --data '{
        "messages": [
          {
            "role": "system",
            "content": "You are a friendly chatbot"
          },
          {
            "role": "assistant",
            "content": "Hello, I'm a friendly bot"
          },
          {
            "role": "user",
            "content": "Hello bot, what is the capital of England?"
          }
        ]
      }'
      ```
    </CodeGroup>
  </Accordion>

  <Accordion defaultOpen="false" title="Add params">
    <CodeGroup>
      ```javascript javascript theme={null}
      import Bytez from 'bytez.js';

      // insert your key
      const sdk = new Bytez('BYTEZ_KEY');

      // choose your model
      const model = sdk.model('Qwen/Qwen3-4B');

      // provide the model with input
      const input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ];

      // provide the model with params
      const params = {
        "temperature": 0
      };

      // send to the model
      const { error, output } = await model.run(input, params);

      // observe the output
      console.log({ error, output });

      ```

      ```python python theme={null}
      from bytez import Bytez

      # insert your key
      sdk = Bytez("BYTEZ_KEY")

      # choose your model
      model = sdk.model("Qwen/Qwen3-4B")

      # provide the model with input
      input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ]

      # provide the model with params
      params = {
        "temperature": 0
      }

      # send to the model
      result = model.run(input, params)

      # observe the output
      print({"error": result.error, "output": result.output})

      ```

      ```bash http theme={null}
      curl -X POST 'https://api.bytez.com/models/v2/Qwen/Qwen3-4B' \
      -H 'Authorization: BYTEZ_KEY' \
      -H 'Content-Type: application/json' \
      --data '{
        "messages": [
          {
            "role": "system",
            "content": "You are a friendly chatbot"
          },
          {
            "role": "assistant",
            "content": "Hello, I'm a friendly bot"
          },
          {
            "role": "user",
            "content": "Hello bot, what is the capital of England?"
          }
        ],
        "params": {
          "temperature": 0
        }
      }'
      ```
    </CodeGroup>
  </Accordion>

  <Accordion defaultOpen="false" title="Stream text">
    <CodeGroup>
      ```javascript javascript theme={null}
      import Bytez from 'bytez.js';

      // insert your key
      const sdk = new Bytez('BYTEZ_KEY');

      // choose your model
      const model = sdk.model('Qwen/Qwen3-4B');

      // provide the model with input
      const input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ];

      // set streaming to "true"
      const stream = true;

      // send to the model
      const readStream = await model.run(input, stream);

      let text = '';

      for await (const tokens of readStream) {
        text += tokens;

        console.log(tokens);
      }

      // observe the output
      console.log({ text });

      ```

      ```python python theme={null}
      from bytez import Bytez

      # insert your key
      sdk = Bytez("BYTEZ_KEY")

      # choose your model
      model = sdk.model("Qwen/Qwen3-4B")

      # provide the model with input
      input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ]

      # set streaming to "true"
      stream = True

      # send to the model
      readStream = model.run(input, stream=stream)

      text = ""

      for tokens in readStream:
          text += tokens

          print(tokens)

      # observe the output
      print({"text": text})

      ```

      ```bash http theme={null}
      curl -X POST 'https://api.bytez.com/models/v2/Qwen/Qwen3-4B' \
      -H 'Authorization: BYTEZ_KEY' \
      -H 'Content-Type: application/json' \
      --data '{
        "messages": [
          {
            "role": "system",
            "content": "You are a friendly chatbot"
          },
          {
            "role": "assistant",
            "content": "Hello, I'm a friendly bot"
          },
          {
            "role": "user",
            "content": "Hello bot, what is the capital of England?"
          }
        ],
        "stream": true
      }'
      ```
    </CodeGroup>
  </Accordion>

  <Accordion defaultOpen="false" title="Add params + Stream text">
    <CodeGroup>
      ```javascript javascript theme={null}
      import Bytez from 'bytez.js';

      // insert your key
      const sdk = new Bytez('BYTEZ_KEY');

      // choose your model
      const model = sdk.model('Qwen/Qwen3-4B');

      // provide the model with input
      const input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ];

      // provide the model with params
      const params = {
        "temperature": 0
      };

      // set streaming to "true"
      const stream = true;

      // send to the model
      const readStream = await model.run(input, params, stream);

      let text = '';

      for await (const tokens of readStream) {
        text += tokens;

        console.log(tokens);
      }

      // observe the output
      console.log({ text });

      ```

      ```python python theme={null}
      from bytez import Bytez

      # insert your key
      sdk = Bytez("BYTEZ_KEY")

      # choose your model
      model = sdk.model("Qwen/Qwen3-4B")

      # provide the model with input
      input = [
        {
          "role": "system",
          "content": "You are a friendly chatbot"
        },
        {
          "role": "assistant",
          "content": "Hello, I'm a friendly bot"
        },
        {
          "role": "user",
          "content": "Hello bot, what is the capital of England?"
        }
      ]

      # provide the model with params
      params = {
        "temperature": 0
      }

      # set streaming to "true"
      stream = True

      # send to the model
      readStream = model.run(input, params, stream)

      text = ""

      for tokens in readStream:
          text += tokens

          print(tokens)

      # observe the output
      print({"text": text})

      ```

      ```bash http theme={null}
      curl -X POST 'https://api.bytez.com/models/v2/Qwen/Qwen3-4B' \
      -H 'Authorization: BYTEZ_KEY' \
      -H 'Content-Type: application/json' \
      --data '{
        "messages": [
          {
            "role": "system",
            "content": "You are a friendly chatbot"
          },
          {
            "role": "assistant",
            "content": "Hello, I'm a friendly bot"
          },
          {
            "role": "user",
            "content": "Hello bot, what is the capital of England?"
          }
        ],
        "params": {
          "temperature": 0
        },
        "stream": true
      }'
      ```
    </CodeGroup>
  </Accordion>
</AccordionGroup>