Amazon Bedrock · Schema

Amazon Bedrock Foundation Model

Schema representing an Amazon Bedrock foundation model and its capabilities.

Artificial IntelligenceFoundation ModelsGenerative AILLMMachine-LearningRAGAgentsResponsible AI

Properties

Name Type Description
modelArn string The Amazon Resource Name (ARN) of the foundation model.
modelId string The unique identifier for the foundation model (e.g., anthropic.claude-3-sonnet-20240229-v1:0).
modelName string The display name of the foundation model.
providerName string The name of the model provider.
inputModalities array The input modalities supported by the model.
outputModalities array The output modalities supported by the model.
responseStreamingSupported boolean Whether the model supports response streaming.
customizationsSupported array The customization types supported by the model.
inferenceTypesSupported array The inference types supported by the model.
modelLifecycle object Lifecycle information for the model.
View JSON Schema on GitHub

JSON Schema

amazon-bedrock-model-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://aws.amazon.com/bedrock/schemas/foundation-model.json",
  "title": "Amazon Bedrock Foundation Model",
  "description": "Schema representing an Amazon Bedrock foundation model and its capabilities.",
  "type": "object",
  "required": [
    "modelId",
    "modelName",
    "providerName"
  ],
  "properties": {
    "modelArn": {
      "type": "string",
      "description": "The Amazon Resource Name (ARN) of the foundation model.",
      "pattern": "^arn:aws:bedrock:[a-z0-9-]+::foundation-model/.+$"
    },
    "modelId": {
      "type": "string",
      "description": "The unique identifier for the foundation model (e.g., anthropic.claude-3-sonnet-20240229-v1:0).",
      "examples": [
        "anthropic.claude-3-sonnet-20240229-v1:0",
        "amazon.titan-text-express-v1",
        "meta.llama3-70b-instruct-v1:0"
      ]
    },
    "modelName": {
      "type": "string",
      "description": "The display name of the foundation model."
    },
    "providerName": {
      "type": "string",
      "description": "The name of the model provider.",
      "examples": [
        "Amazon",
        "Anthropic",
        "Meta",
        "Cohere",
        "AI21 Labs",
        "Stability AI",
        "Mistral AI"
      ]
    },
    "inputModalities": {
      "type": "array",
      "description": "The input modalities supported by the model.",
      "items": {
        "type": "string",
        "enum": [
          "TEXT",
          "IMAGE",
          "EMBEDDING"
        ]
      }
    },
    "outputModalities": {
      "type": "array",
      "description": "The output modalities supported by the model.",
      "items": {
        "type": "string",
        "enum": [
          "TEXT",
          "IMAGE",
          "EMBEDDING"
        ]
      }
    },
    "responseStreamingSupported": {
      "type": "boolean",
      "description": "Whether the model supports response streaming."
    },
    "customizationsSupported": {
      "type": "array",
      "description": "The customization types supported by the model.",
      "items": {
        "type": "string",
        "enum": [
          "FINE_TUNING",
          "CONTINUED_PRE_TRAINING"
        ]
      }
    },
    "inferenceTypesSupported": {
      "type": "array",
      "description": "The inference types supported by the model.",
      "items": {
        "type": "string",
        "enum": [
          "ON_DEMAND",
          "PROVISIONED"
        ]
      }
    },
    "modelLifecycle": {
      "type": "object",
      "description": "Lifecycle information for the model.",
      "properties": {
        "status": {
          "type": "string",
          "description": "The lifecycle status of the model.",
          "enum": [
            "ACTIVE",
            "LEGACY"
          ]
        }
      }
    }
  },
  "additionalProperties": false
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/amazon-bedrock-model"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.