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

# Create a response

> Generate model output with the Responses workflow

| Field                                  | Type         | Required | Description                                    |
| -------------------------------------- | ------------ | -------- | ---------------------------------------------- |
| `model`                                | string       | Yes      | Model ID.                                      |
| `input`                                | string/array | Yes      | Text or input-item list.                       |
| `instructions`                         | string       | No       | System-level instructions.                     |
| `max_output_tokens`                    | integer      | No       | Maximum output tokens.                         |
| `stream`                               | boolean      | No       | Return typed SSE events.                       |
| `tools`, `tool_choice`                 | mixed        | No       | Tool definitions and selection policy.         |
| `text`                                 | object       | No       | Text format, including JSON Schema.            |
| `temperature`, `top_p`                 | number       | No       | Sampling settings.                             |
| `previous_response_id`                 | string       | No       | Continue a previous response.                  |
| `store`, `metadata`, `user`, `include` | mixed        | No       | Storage, metadata, user ID, and included data. |

<CodeGroup>
  ```bash cURL theme={null}
  curl https://api.bianxie.ai/v1/responses \
    -H "Authorization: Bearer API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "your-model",
      "input": "Hello"
    }'
  ```

  ```python Python theme={null}
  client.responses.create(model="your-model", input="Hello")
  ```

  ```javascript Node.js theme={null}
  await client.responses.create({ model: "your-model", input: "Hello" });
  ```
</CodeGroup>

The response includes `id`, `status`, `model`, `output[]`, `usage`, and error details. Text is generally carried by `output_text` content items. Streaming returns typed response events.