CompletionRequestV2

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/scale-ai/json-schema/scale-ai-completion-request-v2-schema.json",
  "title": "CompletionRequestV2",
  "x-generated": "2026-10-27",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/scale-ai-sgp-v4-openapi.yml#/components/schemas/CompletionRequestV2",
  "properties": {
    "model_request_parameters": {
      "$ref": "#/$defs/ParameterBindings"
    },
    "temperature": {
      "title": "Temperature",
      "description": "What sampling temperature to use, between [0, 2]. Higher values like 1.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Setting temperature=0.0 will enable fully deterministic (greedy) sampling.NOTE: The temperature parameter range for some model is limited to [0, 1] if the given value is above the available range, it defaults to the max value. Temperature is ignored for OpenAI reasoning models.",
      "default": 0.2,
      "type": "number",
      "maximum": 2,
      "minimum": 0
    },
    "stop_sequences": {
      "title": "Stop Sequences",
      "description": "List of up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.",
      "items": {
        "type": "string"
      },
      "type": "array",
      "maxItems": 4
    },
    "max_tokens": {
      "title": "Max Tokens",
      "description": "The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. If not, specified, max_tokens will be determined based on the model used: \n| Model API family | Model API default | EGP applied default |\n| --- | --- | --- |\n| OpenAI Completions | [`16`](https://platform.openai.com/docs/api-reference/completions/create#max_tokens) | `context window - prompt size` |\n| OpenAI Chat Completions | [`context window - prompt size`](https://platform.openai.com/docs/api-reference/chat/create#max_tokens) | `context window - prompt size` |\n| LLM Engine | [`max_new_tokens`](https://github.com/scaleapi/launch-python-client/blob/207adced1c88c1c2907266fa9dd1f1ff3ec0ea5b/launch/client.py#L2910) parameter is required | `100` |\n| Anthropic Claude 2 | [`max_tokens_to_sample`](https://docs.anthropic.com/claude/reference/complete_post) parameter is required | `10000` |\n",
      "type": "integer"
    },
    "top_p": {
      "title": "Top P",
      "description": "The cumulative probability cutoff for token selection. Lower values mean sampling from a smaller, more top-weighted nucleus. Available for models provided by Google, LLM Engine, and OpenAI.",
      "type": "number"
    },
    "top_k": {
      "title": "Top K",
      "description": "Sample from the k most likely next tokens at each step. Lower k focuses on higher probability tokens. Available for models provided by Google and LLM Engine.",
      "type": "number"
    },
    "frequency_penalty": {
      "title": "Frequency Penalty",
      "description": "Penalize tokens based on how much they have already appeared in the text. Positive values encourage the model to generate new tokens and negative values encourage the model to repeat tokens. Available for models provided by LLM Engine and OpenAI.",
      "type": "number"
    },
    "presence_penalty": {
      "title": "Presence Penalty",
      "description": "Penalize tokens based on if they have already appeared in the text. Positive values encourage the model to generate new tokens and negative values encourage the model to repeat tokens. Available for models provided by LLM Engine and OpenAI.",
      "type": "number"
    },
    "stream": {
      "title": "Stream",
      "description": "Flag indicating whether to stream the completion response",
      "default": false,
      "type": "boolean"
    },
    "logprobs": {
      "title": "Logprobs",
      "description": "Whether to return logprobs. Currently only supported for llmengine chat models.",
      "type": "boolean"
    },
    "top_logprobs": {
      "title": "Top Logprobs",
      "description": "Number of top logprobs to return. Currently only supported for llmengine chat models.",
      "type": "integer"
    },
    "chat_template": {
      "title": "Chat Template",
      "description": "The chat template to use for the completion. Currently only supported for llmengine chat models.",
      "type": "string"
    },
    "chat_template_kwargs": {
      "title": "Chat Template Kwargs",
      "description": "Additional keyword arguments for the chat template. Currently only supported for llmengine chat models.",
      "additionalProperties": true,
      "type": "object"
    },
    "reasoning_effort": {
      "title": "Reasoning Effort",
      "description": "The reasoning effort to use for the completion. Currently only supported for openai models.",
      "type": "string",
      "enum": [
        "low",
        "medium",
        "high"
      ]
    },
    "prompt": {
      "type": "string",
      "title": "Prompt"
    }
  },
  "additionalProperties": false,
  "type": "object",
  "required": [
    "prompt"
  ],
  "$defs": {
    "ParameterBindings": {
      "properties": {
        "bindings": {
          "additionalProperties": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "integer"
              },
              {
                "type": "number"
              },
              {
                "type": "boolean"
              }
            ]
          },
          "type": "object",
          "title": "Bindings"
        }
      },
      "additionalProperties": false,
      "type": "object",
      "required": [
        "bindings"
      ],
      "title": "ParameterBindings"
    }
  }
}