Anthropic · Schema

ModelInfo

LLMAnthropicArtificial IntelligenceClaudeFoundation ModelsMachine LearningMCPAgents

Properties

Name Type Description
capabilities object Object mapping capability names to their support details. Keys are always present for all known capabilities.
created_at string RFC 3339 datetime string representing the time at which the model was released. May be set to an epoch value if the release date is unknown.
display_name string A human-readable name for the model.
id string Unique model identifier.
max_input_tokens object Maximum input context window size in tokens for this model.
max_tokens object Maximum value for the `max_tokens` parameter when using this model.
type string Object type. For Models, this is always `"model"`.
View JSON Schema on GitHub

JSON Schema

anthropic-model-info-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/anthropic/main/json-schema/anthropic-model-info-schema.json",
  "title": "ModelInfo",
  "x-generated": "2026-09-23",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/anthropic-models-api-openapi.yml#/components/schemas/ModelInfo",
  "properties": {
    "capabilities": {
      "anyOf": [
        {
          "$ref": "#/$defs/ModelCapabilities"
        },
        {
          "type": "null"
        }
      ],
      "description": "Object mapping capability names to their support details. Keys are always present for all known capabilities."
    },
    "created_at": {
      "type": "string",
      "format": "date-time",
      "title": "Created At",
      "description": "RFC 3339 datetime string representing the time at which the model was released. May be set to an epoch value if the release date is unknown."
    },
    "display_name": {
      "type": "string",
      "title": "Display Name",
      "description": "A human-readable name for the model."
    },
    "id": {
      "type": "string",
      "title": "Id",
      "description": "Unique model identifier."
    },
    "max_input_tokens": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Max Input Tokens",
      "description": "Maximum input context window size in tokens for this model."
    },
    "max_tokens": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Max Tokens",
      "description": "Maximum value for the `max_tokens` parameter when using this model."
    },
    "type": {
      "type": "string",
      "const": "model",
      "title": "Type",
      "description": "Object type.\n\nFor Models, this is always `\"model\"`.",
      "default": "model"
    }
  },
  "type": "object",
  "required": [
    "capabilities",
    "created_at",
    "display_name",
    "id",
    "max_input_tokens",
    "max_tokens",
    "type"
  ],
  "$defs": {
    "CapabilitySupport": {
      "properties": {
        "supported": {
          "type": "boolean",
          "title": "Supported",
          "description": "Whether this capability is supported by the model."
        }
      },
      "type": "object",
      "required": [
        "supported"
      ],
      "title": "CapabilitySupport",
      "description": "Indicates whether a capability is supported."
    },
    "ContextManagementCapability": {
      "properties": {
        "clear_thinking_20251015": {
          "anyOf": [
            {
              "$ref": "#/$defs/CapabilitySupport"
            },
            {
              "type": "null"
            }
          ],
          "description": "Whether the clear_thinking_20251015 strategy is supported."
        },
        "clear_tool_uses_20250919": {
          "anyOf": [
            {
              "$ref": "#/$defs/CapabilitySupport"
            },
            {
              "type": "null"
            }
          ],
          "description": "Whether the clear_tool_uses_20250919 strategy is supported."
        },
        "compact_20260112": {
          "anyOf": [
            {
              "$ref": "#/$defs/CapabilitySupport"
            },
            {
              "type": "null"
            }
          ],
          "description": "Whether the compact_20260112 strategy is supported."
        },
        "supported": {
          "type": "boolean",
          "title": "Supported",
          "description": "Whether this capability is supported by the model."
        }
      },
      "type": "object",
      "required": [
        "clear_thinking_20251015",
        "clear_tool_uses_20250919",
        "compact_20260112",
        "supported"
      ],
      "title": "ContextManagementCapability",
      "description": "Context management capability details."
    },
    "EffortCapability": {
      "properties": {
        "high": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports high effort level."
        },
        "low": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports low effort level."
        },
        "max": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports max effort level."
        },
        "medium": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports medium effort level."
        },
        "supported": {
          "type": "boolean",
          "title": "Supported",
          "description": "Whether this capability is supported by the model."
        },
        "xhigh": {
          "anyOf": [
            {
              "$ref": "#/$defs/CapabilitySupport"
            },
            {
              "type": "null"
            }
          ],
          "description": "Whether the model supports xhigh effort level."
        }
      },
      "type": "object",
      "required": [
        "high",
        "low",
        "max",
        "medium",
        "supported",
        "xhigh"
      ],
      "title": "EffortCapability",
      "description": "Effort (reasoning_effort) capability details."
    },
    "ModelCapabilities": {
      "properties": {
        "batch": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports the Batch API."
        },
        "citations": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports citation generation."
        },
        "code_execution": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports code execution tools."
        },
        "context_management": {
          "$ref": "#/$defs/ContextManagementCapability",
          "description": "Context management support and available strategies."
        },
        "effort": {
          "$ref": "#/$defs/EffortCapability",
          "description": "Effort (reasoning_effort) support and available levels."
        },
        "image_input": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model accepts image content blocks."
        },
        "pdf_input": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model accepts PDF content blocks."
        },
        "structured_outputs": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports structured output / JSON mode / strict tool schemas."
        },
        "thinking": {
          "$ref": "#/$defs/ThinkingCapability",
          "description": "Thinking capability and supported type configurations."
        }
      },
      "type": "object",
      "required": [
        "batch",
        "citations",
        "code_execution",
        "context_management",
        "effort",
        "image_input",
        "pdf_input",
        "structured_outputs",
        "thinking"
      ],
      "title": "ModelCapabilities",
      "description": "Model capability information."
    },
    "ThinkingCapability": {
      "properties": {
        "supported": {
          "type": "boolean",
          "title": "Supported",
          "description": "Whether this capability is supported by the model."
        },
        "types": {
          "$ref": "#/$defs/ThinkingTypes"
        }
      },
      "type": "object",
      "required": [
        "supported",
        "types"
      ],
      "title": "ThinkingCapability",
      "description": "Thinking capability details."
    },
    "ThinkingTypes": {
      "properties": {
        "adaptive": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports thinking with type 'adaptive' (auto)."
        },
        "enabled": {
          "$ref": "#/$defs/CapabilitySupport",
          "description": "Whether the model supports thinking with type 'enabled'."
        }
      },
      "type": "object",
      "required": [
        "adaptive",
        "enabled"
      ],
      "title": "ThinkingTypes",
      "description": "Supported thinking type configurations."
    }
  }
}

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/anthropic-model-info"
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 form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

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