Vercel AI Gateway Chat Completion Request

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/vercel/main/json-schema/vercel-chat-completion-schema.json",
  "title": "Vercel AI Gateway Chat Completion Request",
  "description": "Schema for a chat completion request to the Vercel AI Gateway (OpenAI-compatible format).",
  "type": "object",
  "required": ["model", "messages"],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model identifier in provider/model-name format (e.g., 'anthropic/claude-opus-4.6')",
      "examples": ["anthropic/claude-opus-4.6", "openai/gpt-4o", "google/gemini-2.0-flash"]
    },
    "messages": {
      "type": "array",
      "description": "Conversation messages",
      "items": {
        "type": "object",
        "required": ["role", "content"],
        "properties": {
          "role": {
            "type": "string",
            "enum": ["system", "user", "assistant", "tool"],
            "description": "Message role"
          },
          "content": {
            "oneOf": [
              { "type": "string" },
              {
                "type": "array",
                "items": {
                  "type": "object",
                  "properties": {
                    "type": { "type": "string", "enum": ["text", "image_url"] },
                    "text": { "type": "string" },
                    "image_url": {
                      "type": "object",
                      "properties": {
                        "url": { "type": "string" },
                        "detail": { "type": "string", "enum": ["auto", "low", "high"] }
                      }
                    }
                  }
                }
              }
            ]
          }
        }
      }
    },
    "stream": {
      "type": "boolean",
      "default": false,
      "description": "Whether to stream the response via SSE"
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 2,
      "description": "Sampling temperature"
    },
    "max_tokens": {
      "type": "integer",
      "description": "Maximum tokens to generate"
    },
    "providerOptions": {
      "type": "object",
      "description": "Gateway provider routing options",
      "properties": {
        "gateway": {
          "type": "object",
          "properties": {
            "order": {
              "type": "array",
              "items": { "type": "string" },
              "description": "Ordered provider fallback chain"
            },
            "sort": {
              "type": "string",
              "enum": ["cost", "ttft", "tps"]
            }
          }
        }
      }
    },
    "provider": {
      "type": "object",
      "description": "Provider shorthand options",
      "properties": {
        "sort": {
          "type": "string",
          "enum": ["cost", "ttft", "tps"],
          "description": "Sort providers by cost, time-to-first-token, or tokens-per-second"
        }
      }
    }
  }
}