{"title":"Async Batch","type":"object","properties":{"requests":{"type":"array","items":{"type":"object","properties":{"external_reference":{"type":"string","description":"User-supplied reference. This field will be present in the response as well it can be used to reference the request and response. It's NOT validated to be unique."},"prompt":{"type":"string","minLength":1,"description":"Prompt for the text generation model"},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"response_format":{"title":"JSON Mode","type":"object","properties":{"type":{"type":"string","enum":["json_object","json_schema"]},"json_schema":{}}}}}}}}