{ "$schema": "https://json-schema.org/draft/2020-12/schema", "$id": "https://artifacts.apis.io/scale-ai/json-schema/scale-ai-create-chat-completion-request-schema.json", "title": "CreateChatCompletionRequest", "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/CreateChatCompletionRequest", "properties": { "account_id": { "title": "Account Id", "description": "The account ID to use for usage tracking. This will be gradually enforced.", "type": "string" }, "model": { "type": "string", "enum": [ "gpt-oss-120b", "gpt-oss-20b", "o1", "o1-mini", "o3-mini", "gpt-4", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-4o", "gpt-4o-mini", "gpt-4o-2024-08-06", "gpt-3.5-turbo", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gemini-pro", "gemini-1.5-pro-001", "gemini-1.5-pro-002", "gemini-1.5-pro-preview-0409", "gemini-1.5-pro-preview-0514", "llama-2-7b-chat", "llama-2-13b-chat", "llama-2-70b-chat", "llama-3-8b-instruct", "llama-3-70b-instruct", "llama-3-1-8b-instruct", "llama-3-1-70b-instruct", "llama-3-2-1b-instruct", "llama-3-2-3b-instruct", "llama-3-3-70b-instruct", "Meta-Llama-3-8B-Instruct-RMU", "Meta-Llama-3-8B-Instruct-RR", "Meta-Llama-3-8B-Instruct-DERTA", "Meta-Llama-3-8B-Instruct-LAT", "mixtral-8x7b-instruct", "mixtral-8x22b-instruct", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-sonnet-20240620", "claude-3-5-sonnet-20241022", "mistral-large-latest", "phi-3-mini-4k-instruct", "phi-3-cat-merged", "zephyr-cat-merged", "dolphin-2.9-llama3-8b", "dolphin-2.9-llama3-70b", "defense-llama-3-8b-instruct", "donovan-combat-llama", "llama3-1-405b-instruct-v1" ], "title": "Model", "description": "The ID of the model to use for chat completions. We only support the models listed here so far." }, "memory_strategy": { "$ref": "#/$defs/MemoryStrategy", "description": "The memory strategy to use for the agent. A memory strategy is a way to prevent the underlying LLM's context limit from being exceeded. Each memory strategy uses a different technique to condense the input message list into a smaller payload for the underlying LLM.\n\nWe only support the Last K memory strategy right now, but will be adding new strategies soon." }, "messages": { "items": { "$ref": "#/$defs/ChatMessage" }, "type": "array", "title": "Messages", "description": "The list of messages in the conversation.\n\nExpand each message type to see how it works and when to use it. Most conversations should begin with a single `user` message." }, "model_parameters": { "$ref": "#/$defs/ModelParameters", "description": "Configuration parameters for the chat completion model, such as temperature, max_tokens, and stop_sequences.\n\nIf not specified, the default value are:\n- temperature: 0.2\n- max_tokens: None (limited by the model's max tokens)\n- stop_sequences: None", "default": { "temperature": 0.2 } }, "instructions": { "title": "Instructions", "description": "The initial instructions to provide to the chat completion model.\n\nUse this to guide the model to act in more specific ways. For example, if you have specific rules you want to restrict the model to follow you can specify them here.\n\nGood prompt engineering is crucial to getting performant results from the model. If you are having trouble getting the model to perform well, try writing more specific instructions here before trying more expensive techniques such as swapping in other models or finetuning the underlying LLM.", "default": "You are an AI assistant that helps users with their questions by chatting back and forth with them. When asked a question, you should answer it as best as you can with the information you have. If you need more information, you can ask the user for it.", "type": "string" }, "chat_template": { "title": "Chat Template", "description": "Currently only supported for LLM-Engine models. A Jinja template string that defines how the chat completion API formats the string prompt. For Llama models, the template must take in at most a `messages` object, `bos_token` string, and `eos_token` string. The `messages` object is a list of dictionaries, each with keys `role` and `content`. For Mixtral models, the template must take in at most a `messages` object and `eos_token` string. The `messages` object looks identical to the Llama model's `messages` object, but the template can assume the `role` key takes on the values `user` or `assistant`, or `system` for the first message. The chat template either needs to handle this system message (which gets set via the `instructions` field or by the messages), or the `instructions` field must be set to `null` and the `messages` object must not contain any system messages.See the default chat template present in the Llama and Mixtral tokenizers for examples.", "type": "string" }, "stream": { "type": "boolean", "title": "Stream", "description": "Whether or not to stream the response.\n\nSetting this to True will stream the completion in real-time.", "default": false } }, "type": "object", "required": [ "model", "messages" ], "$defs": { "AssistantMessage": { "properties": { "role": { "type": "string", "const": "assistant", "title": "Role", "description": "The role of the message. Must be set to 'assistant'.\n\nAn assistant message is a message from the AI to the client. It is different from an agent message in that it cannot contain a tool request. It is simply a direct response from the AI to the client.", "default": "assistant" }, "content": { "type": "string", "title": "Content", "description": "Text response from the assistant" } }, "type": "object", "required": [ "content" ], "title": "Assistant Message" }, "ChatMessage": { "oneOf": [ { "$ref": "#/$defs/UserMessage" }, { "$ref": "#/$defs/AssistantMessage" }, { "$ref": "#/$defs/SystemMessage" } ], "title": "ChatMessage" }, "ImageDataSubPart": { "properties": { "type": { "type": "string", "const": "base64", "title": "Type", "description": "The type of the image data. Only base64 is supported.", "default": "base64" }, "media_type": { "type": "string", "title": "Media Type", "description": "The media/mime type of the image data. For example, 'image/png'. Check providers' documentation for supported media types." }, "data": { "type": "string", "title": "Data", "description": "The base64-encoded image data." }, "detail": { "title": "Detail", "description": "Only used for OpenAI. Corresponds to OpenAI's image detail parameter.", "type": "string", "enum": [ "low", "high", "auto" ] } }, "type": "object", "required": [ "media_type", "data" ], "title": "ImageDataSubPart" }, "ImageDataUserMessageContentParts": { "properties": { "type": { "type": "string", "const": "image_data", "title": "Type", "default": "image_data" }, "image_data": { "$ref": "#/$defs/ImageDataSubPart", "description": "Specifies inline image data" } }, "type": "object", "required": [ "image_data" ], "title": "ImageDataUserMessageContentParts" }, "ImageUrlSubPart": { "properties": { "url": { "type": "string", "title": "Url", "description": "The URL of the image. Note: only OpenAI supports this." }, "detail": { "title": "Detail", "description": "Only used for OpenAI. Corresponds to OpenAI's image detail parameter.", "type": "string", "enum": [ "low", "high", "auto" ] } }, "type": "object", "required": [ "url" ], "title": "ImageUrlSubPart" }, "ImageUrlUserMessageContentParts": { "properties": { "type": { "type": "string", "const": "image_url", "title": "Type", "default": "image_url" }, "image_url": { "$ref": "#/$defs/ImageUrlSubPart", "description": "Specifies the image URL and level of detail. Only supported by OpenAI models" } }, "type": "object", "required": [ "image_url" ], "title": "ImageUrlUserMessageContentParts" }, "LastKMemoryStrategy": { "properties": { "name": { "type": "string", "const": "last_k", "title": "Name", "description": "Name of the memory strategy. Must be `last_k`.\n\nThis strategy truncates the message history to the last `k` messages. It is the simplest way to prevent the model's context limit from being exceeded. However, this strategy only allows the model to have short term memory. For longer term memory, please use one of the other strategies.", "default": "last_k" }, "params": { "$ref": "#/$defs/LastKMemoryStrategyParams", "description": "Configuration parameters for the memory strategy." } }, "type": "object", "required": [ "params" ], "title": "Last K Memory Strategy" }, "LastKMemoryStrategyParams": { "properties": { "k": { "type": "integer", "minimum": 1, "title": "K", "description": "The maximum number of previous messages to remember." } }, "type": "object", "required": [ "k" ], "title": "LastKMemoryStrategyParams" }, "MemoryStrategy": { "$ref": "#/$defs/LastKMemoryStrategy", "title": "MemoryStrategy" }, "ModelParameters": { "properties": { "temperature": { "title": "Temperature", "description": "What sampling temperature to use, between [0, 1]. Higher values like 0.8 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. Temperature is ignored for OpenAI reasoning models.", "default": 0.2, "type": "number", "maximum": 1, "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" }, "topP": { "title": "Topp", "description": "The cumulative probability cutoff for token selection. Lower values mean sampling from a smaller, more top-weighted nucleus. Available for models from Anthropic, Google, Mistral, LLM Engine, and OpenAI.", "type": "number" }, "topK": { "title": "Topk", "description": "Sample from the k most likely next tokens at each step. Lower k focuses on higher probability tokens. Available for models from Anthropic, Google, and LLM Engine.", "type": "integer" }, "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 from 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 from LLM Engine, and OpenAI.", "type": "number" }, "reasoning_effort": { "title": "Reasoning Effort", "description": "The effort level for the model to reason. Available for models from OpenAI.", "type": "string", "enum": [ "low", "medium", "high" ] } }, "type": "object", "title": "ModelParameters" }, "SystemMessage": { "properties": { "role": { "type": "string", "const": "system", "title": "Role", "description": "The role of the message. Must be set to 'system'.\n\nA system message is different from other messages in that it does not originate from a party engaged in a user/AI conversation. Instead, it is a message that is injected by either the application or system to guide the conversation. For example, a system message may be used as initial instructions for an AI entity or to tell the AI that it did not do something correctly.", "default": "system" }, "content": { "type": "string", "title": "Content", "description": "Text input from the system." } }, "type": "object", "required": [ "content" ], "title": "System Message" }, "TextUserMessageContentParts": { "properties": { "type": { "type": "string", "const": "text", "title": "Type", "default": "text" }, "text": { "type": "string", "title": "Text" } }, "type": "object", "required": [ "text" ], "title": "TextUserMessageContentParts" }, "UserMessage": { "properties": { "role": { "type": "string", "const": "user", "title": "Role", "description": "The role of the message. Must be set to 'user'.\n\nA user message is a message from the user to the AI. This should be the message used to send end user input to the AI.", "default": "user" }, "content": { "anyOf": [ { "type": "string" }, { "items": { "$ref": "#/$defs/UserMessageContentParts" }, "type": "array" } ], "title": "Content", "description": "Input from the user. Can either be text or a list of content parts. Not all models support image content parts, or multiple parts." } }, "type": "object", "required": [ "content" ], "title": "User Message" }, "UserMessageContentParts": { "oneOf": [ { "$ref": "#/$defs/TextUserMessageContentParts" }, { "$ref": "#/$defs/ImageUrlUserMessageContentParts" }, { "$ref": "#/$defs/ImageDataUserMessageContentParts" } ], "title": "UserMessageContentParts" } } }