Request payload for Fill-In-the-Middle (FIM) completion.
| Property | Type | Description |
|---|---|---|
| echo | Boolean | Echo back the prompt in addition to the completion. |
| logprobs | Integer | Include the log probabilities on the most likely output tokens (max 20). |
| max_tokens | Integer | The maximum number of tokens to generate. |
| model | String | ID of the model to use (e.g. deepseek-flash, deepseek-v4-pro). |
| prompt | String | The prompt to generate completions for. |
| stop | Up to 16 sequences where the API will stop generating tokens. | |
| stream | Boolean | Whether to stream back partial progress via SSE. |
| stream_options | Completion_Stream_Options | Options for streaming responses. |
| suffix | String | The suffix that comes after a completion of inserted text. |
| temperature | Number | Sampling temperature between 0 and 2. |
| top_p | Number | Nucleus sampling probability mass. |