PostV1ChatCompletionsRequest2

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/concentrate/json-schema/concentrate-post-v1-chat-completions-request2-schema.json",
  "title": "PostV1ChatCompletionsRequest2",
  "x-generated": "2026-10-29",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/_ae-authored/concentrate-openapi-generated.yml#/components/schemas/PostV1ChatCompletionsRequest2",
  "type": "object",
  "properties": {
    "messages": {
      "type": "object",
      "description": "A list of messages comprising the conversation so far. Minimum array length: 1"
    },
    "model": {
      "type": "string",
      "description": "Model identifier. Use /v1/models to list all available models. Supports canonical names (e.g. gpt-5.2, claude-opus-4-6), aliases, and provider-prefixed formats (e.g. openai/gpt-5.2). Use \"auto\" for automatic model selection."
    },
    "frequency_penalty": {
      "type": "number",
      "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim."
    },
    "function_call": {
      "type": "string",
      "description": "Deprecated in favor of the tool_calls parameter. Will be converted to tool_choice. Available options: none, auto"
    },
    "functions": {
      "type": "object",
      "description": "Deprecated in favor of the tools parameter. Will be converted to tools when used."
    },
    "logit_bias": {
      "type": "object",
      "description": "Unsupported. Modify the likelihood of specified tokens appearing in the completion."
    },
    "logprobs": {
      "type": "boolean",
      "description": "Whether to return log probabilities of the output tokens. If true, logprobs will be included in the response."
    },
    "max_completion_tokens": {
      "type": "number",
      "description": "The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length."
    },
    "max_tokens": {
      "type": "number",
      "description": "Deprecated, use max_completion_tokens instead."
    },
    "metadata": {
      "type": "object",
      "description": "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format."
    },
    "modalities": {
      "type": "string",
      "description": "Unsupported. A list of modalities that the model supports. The model will use these modalities when processing the request. Available options: text, audio"
    },
    "n": {
      "type": "integer",
      "description": "Unsupported. How many chat completion choices to generate for each input message."
    },
    "parallel_tool_calls": {
      "type": "boolean",
      "description": "Whether to enable parallel function calling during tool use."
    },
    "prediction": {
      "type": "object",
      "description": "Unsupported. Specifies the model should predict a specified content, then continue generating naturally."
    },
    "presence_penalty": {
      "type": "number",
      "description": "Unsupported. Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."
    },
    "prompt_cache_key": {
      "type": "string",
      "description": "Optional custom identifier for managing prompt cache entries."
    },
    "prompt_cache_options": {
      "type": "object",
      "description": "OpenAI prompt-cache behavior for this request."
    },
    "prompt_cache_retention": {
      "type": "string",
      "description": "The legacy OpenAI prompt-cache retention policy. Earlier OpenAI models use this field for in-memory or 24-hour retention. GPT-5.6 and later use prompt_cache_options.ttl instead. Available options: in-memory, in_memory, 24h"
    },
    "reasoning_effort": {
      "type": "string",
      "description": "Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Available options: none, minimal, low, medium, high, xhigh, max"
    },
    "response_format": {
      "type": "object",
      "description": "An object specifying the format that the model must output."
    },
    "safety_identifier": {
      "type": "string",
      "description": "Unique identifier to help detect when content may violate usage policies."
    },
    "seed": {
      "type": "integer",
      "description": "Unsupported. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result."
    },
    "service_tier": {
      "type": "string",
      "description": "Specifies which tier to use for processing the request. Available options: auto, default, fast, flex, priority, scale, ultrafast"
    },
    "stop": {
      "type": "string",
      "description": "Unsupported. Up to 4 sequences where the API will stop generating further tokens."
    },
    "store": {
      "type": "boolean",
      "description": "If true, the model's response will be stored for reuse by other requests."
    },
    "stream": {
      "type": "boolean",
      "description": "If true, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available."
    },
    "stream_options": {
      "type": "object",
      "description": "Stream options configuration."
    },
    "temperature": {
      "type": "number",
      "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic."
    },
    "tool_choice": {
      "type": "string",
      "description": "Controls which (if any) function is called by the model. Available options: none, auto, required"
    },
    "tools": {
      "type": "object",
      "description": "A list of tools the model may call."
    },
    "top_logprobs": {
      "type": "integer",
      "description": "An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability."
    },
    "top_p": {
      "type": "number",
      "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass."
    },
    "user": {
      "type": "string",
      "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse."
    },
    "verbosity": {
      "type": "string",
      "description": "Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high. Available options: low, medium, high"
    },
    "web_search_options": {
      "type": "object",
      "description": "Options for web search integration."
    },
    "routing": {
      "type": "object",
      "description": "Concentrate routing configuration controlling how requests are routed across models and providers."
    }
  },
  "required": [
    "messages",
    "model"
  ]
}