Anthropic · Schema
Message
LLMAnthropicArtificial IntelligenceClaudeFoundation ModelsMachine LearningMCPAgents
Properties
| Name | Type | Description |
|---|---|---|
| id | string | Unique object identifier. The format and length of IDs may change over time. |
| type | string | Object type. For Messages, this is always `"message"`. |
| role | string | Conversational role of the generated message. This will always be `"assistant"`. |
| content | array | Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the requ |
| model | object | |
| stop_reason | object | The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's max |
| stop_sequence | object | Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. |
| stop_details | object | Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. |
| usage | object | Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format s |
| diagnostics | object | Request-level diagnostics. Present only when `diagnostics` was supplied on the request; `null` when no prompt-cache divergence was detected. |
| context_management | object | Context management response. Information about context management strategies applied during the request. |
| container | object | Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/api-evangelist/anthropic/main/json-schema/anthropic-beta-message-schema.json",
"title": "Message",
"x-generated": "2026-09-23",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/anthropic-messages-beta-true-api-openapi.yml#/components/schemas/BetaMessage",
"properties": {
"id": {
"description": "Unique object identifier.\n\nThe format and length of IDs may change over time.",
"title": "Id",
"type": "string"
},
"type": {
"const": "message",
"default": "message",
"description": "Object type.\n\nFor Messages, this is always `\"message\"`.",
"title": "Type",
"type": "string"
},
"role": {
"const": "assistant",
"default": "assistant",
"description": "Conversational role of the generated message.\n\nThis will always be `\"assistant\"`.",
"title": "Role",
"type": "string"
},
"content": {
"description": "Content generated by the model.\n\nThis is an array of content blocks, each of which has a `type` that determines its shape.\n\nExample:\n\n```json\n[{\"type\": \"text\", \"text\": \"Hi, I'm Claude.\"}]\n```\n\nIf the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output.\n\nFor example, if the input `messages` were:\n```json\n[\n {\"role\": \"user\", \"content\": \"What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun\"},\n {\"role\": \"assistant\", \"content\": \"The best answer is (\"}\n]\n```\n\nThen the response `content` might be:\n\n```json\n[{\"type\": \"text\", \"text\": \"B)\"}]\n```",
"items": {
"$ref": "#/$defs/BetaContentBlock"
},
"title": "Content",
"type": "array"
},
"model": {
"$ref": "#/$defs/Model"
},
"stop_reason": {
"anyOf": [
{
"$ref": "#/$defs/BetaStopReason"
},
{
"type": "null"
}
],
"description": "The reason that we stopped.\n\nThis may be one the following values:\n* `\"end_turn\"`: the model reached a natural stopping point\n* `\"max_tokens\"`: we exceeded the requested `max_tokens` or the model's maximum\n* `\"stop_sequence\"`: one of your provided custom `stop_sequences` was generated\n* `\"tool_use\"`: the model invoked one or more tools\n* `\"pause_turn\"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.\n* `\"refusal\"`: when streaming classifiers intervene to handle potential policy violations\n* `\"model_context_window_exceeded\"`: we exceeded the model's context window\n\nIn non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise.",
"title": "Stop Reason"
},
"stop_sequence": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Which custom stop sequence was generated, if any.\n\nThis value will be a non-null string if one of your custom stop sequences was generated.",
"title": "Stop Sequence"
},
"stop_details": {
"anyOf": [
{
"$ref": "#/$defs/BetaRefusalStopDetails"
},
{
"type": "null"
}
],
"default": null,
"description": "Structured information about why model output stopped.\n\nThis is `null` when the `stop_reason` has no additional detail to report."
},
"usage": {
"$ref": "#/$defs/BetaUsage",
"description": "Billing and rate-limit usage.\n\nAnthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.\n\nUnder the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response.\n\nFor example, `output_tokens` will be non-zero, even for an empty string response from Claude.\n\nTotal input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`."
},
"diagnostics": {
"anyOf": [
{
"$ref": "#/$defs/BetaDiagnostics"
},
{
"type": "null"
}
],
"default": null,
"description": "Request-level diagnostics. Present only when `diagnostics` was supplied on the request; `null` when no prompt-cache divergence was detected.",
"x-anthropic-beta-required": [
"cache-diagnosis-2026-04-07"
]
},
"context_management": {
"anyOf": [
{
"$ref": "#/$defs/BetaResponseContextManagement"
},
{
"type": "null"
}
],
"default": null,
"description": "Context management response.\n\nInformation about context management strategies applied during the request.",
"x-anthropic-beta-required": [
"context-management-2025-06-27",
"compact-2026-01-12"
]
},
"container": {
"anyOf": [
{
"$ref": "#/$defs/BetaContainer"
},
{
"type": "null"
}
],
"default": null,
"description": "Information about the container used in this request.\n\nThis will be non-null if a container tool (e.g. code execution) was used."
}
},
"required": [
"id",
"type",
"role",
"content",
"model",
"stop_reason",
"stop_sequence",
"stop_details",
"usage",
"diagnostics",
"context_management",
"container"
],
"type": "object",
"x-stainless-python-custom-imports": [
"from .beta_content_block import BetaContentBlock as BetaContentBlock"
],
"$defs": {
"BetaAdvisorMessageIterationUsage": {
"description": "Token usage for an advisor sub-inference iteration.",
"properties": {
"cache_creation": {
"anyOf": [
{
"$ref": "#/$defs/BetaCacheCreation"
},
{
"type": "null"
}
],
"default": null,
"description": "Breakdown of cached tokens by TTL"
},
"cache_creation_input_tokens": {
"default": 0,
"description": "The number of input tokens used to create the cache entry.",
"minimum": 0,
"title": "Cache Creation Input Tokens",
"type": "integer"
},
"cache_read_input_tokens": {
"default": 0,
"description": "The number of input tokens read from the cache.",
"minimum": 0,
"title": "Cache Read Input Tokens",
"type": "integer"
},
"input_tokens": {
"description": "The number of input tokens which were used.",
"minimum": 0,
"title": "Input Tokens",
"type": "integer"
},
"model": {
"$ref": "#/$defs/Model"
},
"output_tokens": {
"description": "The number of output tokens which were used.",
"minimum": 0,
"title": "Output Tokens",
"type": "integer"
},
"type": {
"const": "advisor_message",
"default": "advisor_message",
"description": "Usage for an advisor sub-inference iteration",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_creation",
"cache_creation_input_tokens",
"cache_read_input_tokens",
"input_tokens",
"model",
"output_tokens",
"type"
],
"title": "AdvisorMessageIterationUsage",
"type": "object"
},
"BetaAdvisorToolResultErrorCode": {
"enum": [
"max_uses_exceeded",
"prompt_too_long",
"too_many_requests",
"overloaded",
"unavailable",
"execution_time_exceeded",
"model_not_found"
],
"title": "AdvisorToolResultErrorCode",
"type": "string"
},
"BetaBase64PDFSource": {
"additionalProperties": false,
"properties": {
"data": {
"format": "byte",
"title": "Data",
"type": "string"
},
"media_type": {
"const": "application/pdf",
"title": "Media Type",
"type": "string"
},
"type": {
"const": "base64",
"title": "Type",
"type": "string"
}
},
"required": [
"data",
"media_type",
"type"
],
"title": "Base64PDFSource",
"type": "object"
},
"BetaBashCodeExecutionToolResultErrorCode": {
"enum": [
"invalid_tool_input",
"unavailable",
"too_many_requests",
"execution_time_exceeded",
"output_file_too_large"
],
"title": "BashCodeExecutionToolResultErrorCode",
"type": "string"
},
"BetaCacheCreation": {
"properties": {
"ephemeral_1h_input_tokens": {
"default": 0,
"description": "The number of input tokens used to create the 1 hour cache entry.",
"minimum": 0,
"title": "Ephemeral 1H Input Tokens",
"type": "integer"
},
"ephemeral_5m_input_tokens": {
"default": 0,
"description": "The number of input tokens used to create the 5 minute cache entry.",
"minimum": 0,
"title": "Ephemeral 5M Input Tokens",
"type": "integer"
}
},
"required": [
"ephemeral_1h_input_tokens",
"ephemeral_5m_input_tokens"
],
"title": "CacheCreation",
"type": "object"
},
"BetaCacheMissMessagesChanged": {
"properties": {
"cache_missed_input_tokens": {
"description": "Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.",
"title": "Cache Missed Input Tokens",
"type": "integer"
},
"type": {
"const": "messages_changed",
"default": "messages_changed",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_missed_input_tokens",
"type"
],
"title": "CacheMissMessagesChanged",
"type": "object"
},
"BetaCacheMissModelChanged": {
"properties": {
"cache_missed_input_tokens": {
"description": "Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.",
"title": "Cache Missed Input Tokens",
"type": "integer"
},
"type": {
"const": "model_changed",
"default": "model_changed",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_missed_input_tokens",
"type"
],
"title": "CacheMissModelChanged",
"type": "object"
},
"BetaCacheMissPreviousMessageNotFound": {
"properties": {
"type": {
"const": "previous_message_not_found",
"default": "previous_message_not_found",
"title": "Type",
"type": "string"
}
},
"required": [
"type"
],
"title": "CacheMissPreviousMessageNotFound",
"type": "object"
},
"BetaCacheMissSystemChanged": {
"properties": {
"cache_missed_input_tokens": {
"description": "Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.",
"title": "Cache Missed Input Tokens",
"type": "integer"
},
"type": {
"const": "system_changed",
"default": "system_changed",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_missed_input_tokens",
"type"
],
"title": "CacheMissSystemChanged",
"type": "object"
},
"BetaCacheMissToolsChanged": {
"properties": {
"cache_missed_input_tokens": {
"description": "Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.",
"title": "Cache Missed Input Tokens",
"type": "integer"
},
"type": {
"const": "tools_changed",
"default": "tools_changed",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_missed_input_tokens",
"type"
],
"title": "CacheMissToolsChanged",
"type": "object"
},
"BetaCacheMissUnavailable": {
"properties": {
"type": {
"const": "unavailable",
"default": "unavailable",
"title": "Type",
"type": "string"
}
},
"required": [
"type"
],
"title": "CacheMissUnavailable",
"type": "object"
},
"BetaCodeExecutionToolResultErrorCode": {
"enum": [
"invalid_tool_input",
"unavailable",
"too_many_requests",
"execution_time_exceeded"
],
"title": "CodeExecutionToolResultErrorCode",
"type": "string"
},
"BetaCompactionIterationUsage": {
"description": "Token usage for a compaction iteration.",
"properties": {
"cache_creation": {
"anyOf": [
{
"$ref": "#/$defs/BetaCacheCreation"
},
{
"type": "null"
}
],
"default": null,
"description": "Breakdown of cached tokens by TTL"
},
"cache_creation_input_tokens": {
"default": 0,
"description": "The number of input tokens used to create the cache entry.",
"minimum": 0,
"title": "Cache Creation Input Tokens",
"type": "integer"
},
"cache_read_input_tokens": {
"default": 0,
"description": "The number of input tokens read from the cache.",
"minimum": 0,
"title": "Cache Read Input Tokens",
"type": "integer"
},
"input_tokens": {
"description": "The number of input tokens which were used.",
"minimum": 0,
"title": "Input Tokens",
"type": "integer"
},
"output_tokens": {
"description": "The number of output tokens which were used.",
"minimum": 0,
"title": "Output Tokens",
"type": "integer"
},
"type": {
"const": "compaction",
"default": "compaction",
"description": "Usage for a compaction iteration",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_creation",
"cache_creation_input_tokens",
"cache_read_input_tokens",
"input_tokens",
"output_tokens",
"type"
],
"title": "CompactionIterationUsage",
"type": "object"
},
"BetaContainer": {
"description": "Information about the container used in the request (for the code execution tool)",
"properties": {
"expires_at": {
"description": "The time at which the container will expire.",
"format": "date-time",
"title": "Expires At",
"type": "string"
},
"id": {
"description": "Identifier for the container used in this request",
"title": "Id",
"type": "string"
},
"skills": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/BetaSkill"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Skills loaded in the container",
"title": "Skills"
}
},
"required": [
"expires_at",
"id",
"skills"
],
"title": "Container",
"type": "object"
},
"BetaContentBlock": {
"oneOf": [
{
"$ref": "#/$defs/BetaResponseTextBlock"
},
{
"$ref": "#/$defs/BetaResponseThinkingBlock"
},
{
"$ref": "#/$defs/BetaResponseRedactedThinkingBlock"
},
{
"$ref": "#/$defs/BetaResponseToolUseBlock"
},
{
"$ref": "#/$defs/BetaResponseServerToolUseBlock"
},
{
"$ref": "#/$defs/BetaResponseWebSearchToolResultBlock"
},
{
"$ref": "#/$defs/BetaResponseWebFetchToolResultBlock"
},
{
"$ref": "#/$defs/BetaResponseAdvisorToolResultBlock",
"x-anthropic-beta-required": [
"advisor-tool-2026-03-01"
]
},
{
"$ref": "#/$defs/BetaResponseCodeExecutionToolResultBlock"
},
{
"$ref": "#/$defs/BetaResponseBashCodeExecutionToolResultBlock"
},
{
"$ref": "#/$defs/BetaResponseTextEditorCodeExecutionToolResultBlock"
},
{
"$ref": "#/$defs/BetaResponseToolSearchToolResultBlock"
},
{
"$ref": "#/$defs/BetaResponseMCPToolUseBlock",
"x-anthropic-beta-required": [
"mcp-client-2025-04-04",
"mcp-client-2025-11-20"
]
},
{
"$ref": "#/$defs/BetaResponseMCPToolResultBlock",
"x-anthropic-beta-required": [
"mcp-client-2025-04-04",
"mcp-client-2025-11-20"
]
},
{
"$ref": "#/$defs/BetaResponseContainerUploadBlock"
},
{
"$ref": "#/$defs/BetaResponseCompactionBlock",
"x-anthropic-beta-required": [
"compact-2026-01-12"
]
},
{
"$ref": "#/$defs/BetaResponseFallbackBlock",
"x-anthropic-beta-required": [
"server-side-fallback-2026-06-01",
"server-side-fallback-2026-07-01"
]
}
]
},
"BetaDiagnostics": {
"description": "Response envelope for request-level diagnostics. Present (possibly\nnull) whenever the caller supplied `diagnostics` on the request.",
"properties": {
"cache_miss_reason": {
"anyOf": [
{
"oneOf": [
{
"$ref": "#/$defs/BetaCacheMissModelChanged"
},
{
"$ref": "#/$defs/BetaCacheMissSystemChanged"
},
{
"$ref": "#/$defs/BetaCacheMissToolsChanged"
},
{
"$ref": "#/$defs/BetaCacheMissMessagesChanged"
},
{
"$ref": "#/$defs/BetaCacheMissPreviousMessageNotFound"
},
{
"$ref": "#/$defs/BetaCacheMissUnavailable"
}
]
},
{
"type": "null"
}
],
"default": null,
"description": "Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed.",
"title": "Cache Miss Reason"
}
},
"required": [
"cache_miss_reason"
],
"title": "Diagnostics",
"type": "object"
},
"BetaDirectCaller": {
"additionalProperties": false,
"description": "Tool invocation directly from the model.",
"properties": {
"type": {
"const": "direct",
"title": "Type",
"type": "string"
}
},
"required": [
"type"
],
"title": "DirectCaller",
"type": "object"
},
"BetaFallbackCreditNotApplied": {
"description": "No reprice was applied; ``reason`` says why.",
"properties": {
"reason": {
"description": "Why the reprice was not applied.\n\nA closed enum; additions to the redemption-check vocabulary arrive as\ndeliberate schema updates.",
"enum": [
"body_mismatch",
"continuation_excluded",
"continuation_only",
"expired",
"invalid_target_model",
"not_enabled",
"reprice_unavailable",
"temporarily_unavailable",
"variant_fields_present",
"wrong_organization",
"wrong_platform",
"wrong_workspace"
],
"title": "Reason",
"type": "string"
},
"remove_to_redeem": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Request fields to remove before retrying, so the retry can redeem this\ntoken.\n\nPresent exactly when `reason` is `variant_fields_present` — never null,\nnever an empty array; absent otherwise. Fields are named only from your own request, and only after\nthe sealed variant hash matched. A served best-effort retry has already\nbeen billed at normal price; nothing redeems retroactively, but a corrected\nre-send inside the token's five-minute window can still redeem.",
"title": "Remove To Redeem"
},
"type": {
"const": "not_applied",
"default": "not_applied",
"title": "Type",
"type": "string"
}
},
"required": [
"reason",
"type"
],
"title": "FallbackCreditNotApplied",
"type": "object"
},
"BetaFallbackCreditRedeemed": {
"description": "The reprice was applied: the retry is billed as if the conversation\nhad been on the retry model all along.",
"properties": {
"type": {
"const": "redeemed",
"default": "redeemed",
"title": "Type",
"type": "string"
}
},
"required": [
"type"
],
"title": "FallbackCreditRedeemed",
"type": "object"
},
"BetaFallbackCreditUsage": {
"description": "Outcome of the ``fallback_credit_token`` presented on this request.",
"properties": {
"status": {
"description": "Whether the fallback-credit reprice was applied to this response's billing.\n\nA union discriminated on `type`. `redeemed`: the retry is billed as if\nthe conversation had been on the retry model all along — including when the\nresulting shift is zero because there was nothing to move. `not_applied`:\nno reprice was applied; the arm's `reason` says why.",
"oneOf": [
{
"$ref": "#/$defs/BetaFallbackCreditRedeemed"
},
{
"$ref": "#/$defs/BetaFallbackCreditNotApplied"
}
],
"title": "Status"
}
},
"required": [
"status"
],
"title": "FallbackCreditUsage",
"type": "object"
},
"BetaFallbackMessageIterationUsage": {
"description": "Token usage for the fallback-model attempt of a server-side fallback request.\n\nProduced in place of a `message` entry for whichever hop served the\nresponse. A declined hop produces the existing `message` entry. Whether\na fallback model served the response is signalled by the presence of this\nentry in `usage.iterations`.",
"properties": {
"cache_creation": {
"anyOf": [
{
"$ref": "#/$defs/BetaCacheCreation"
},
{
"type": "null"
}
],
"default": null,
"description": "Breakdown of cached tokens by TTL"
},
"cache_creation_input_tokens": {
"default": 0,
"description": "The number of input tokens used to create the cache entry.",
"minimum": 0,
"title": "Cache Creation Input Tokens",
"type": "integer"
},
"cache_read_input_tokens": {
"default": 0,
"description": "The number of input tokens read from the cache.",
"minimum": 0,
"title": "Cache Read Input Tokens",
"type": "integer"
},
"input_tokens": {
"description": "The number of input tokens which were used.",
"minimum": 0,
"title": "Input Tokens",
"type": "integer"
},
"model": {
"$ref": "#/$defs/Model"
},
"output_tokens": {
"description": "The number of output tokens which were used.",
"minimum": 0,
"title": "Output Tokens",
"type": "integer"
},
"type": {
"const": "fallback_message",
"default": "fallback_message",
"description": "Usage for the fallback-model attempt that served the response",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_creation",
"cache_creation_input_tokens",
"cache_read_input_tokens",
"input_tokens",
"model",
"output_tokens",
"type"
],
"title": "FallbackMessageIterationUsage",
"type": "object"
},
"BetaFallbackRefusalTrigger": {
"description": "The `from` model declined for policy reasons.",
"properties": {
"category": {
"anyOf": [
{
"$ref": "#/$defs/BetaRefusalCategory"
},
{
"type": "null"
}
],
"default": null,
"description": "The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`.",
"x-stainless-naming": {
"csharp": {
"type_name": "BetaFallbackRefusalTriggerCategory"
}
}
},
"type": {
"const": "refusal",
"default": "refusal",
"title": "Type",
"type": "string"
}
},
"required": [
"category",
"type"
],
"title": "FallbackRefusalTrigger",
"type": "object"
},
"BetaIterationsUsage": {
"anyOf": [
{
"items": {
"oneOf": [
{
"$ref": "#/$defs/BetaMessageIterationUsage"
},
{
"$ref": "#/$defs/BetaCompactionIterationUsage"
},
{
"$ref": "#/$defs/BetaAdvisorMessageIterationUsage",
"x-anthropic-beta-required": [
"advisor-tool-2026-03-01"
]
},
{
"$ref": "#/$defs/BetaFallbackMessageIterationUsage",
"x-anthropic-beta-required": [
"server-side-fallback-2026-06-01",
"server-side-fallback-2026-07-01"
]
}
],
"x-stainless-naming": {
"java": {
"type_name": "BetaIterationsUsageItems"
},
"csharp": {
"type_name": "BetaIterationsUsageItems"
}
}
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Per-iteration token usage breakdown.\n\nEach entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to:\n- Determine which iterations exceeded long context thresholds (>=200k tokens)\n- Calculate the context window size from the last `message` entry\n- Understand token accumulation across server-side tool use loops\n\nA `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results.",
"title": "Iterations",
"x-anthropic-beta-required": [
"compact-2026-01-12",
"advisor-tool-2026-03-01",
"task-budgets-2026-03-13",
"server-side-fallback-2026-06-01",
"server-side-fallback-2026-07-01"
]
},
"BetaMessageIterationUsage": {
"description": "Token usage for a sampling iteration.",
"properties": {
"cache_creation": {
"anyOf": [
{
"$ref": "#/$defs/BetaCacheCreation"
},
{
"type": "null"
}
],
"default": null,
"description": "Breakdown of cached tokens by TTL"
},
"cache_creation_input_tokens": {
"default": 0,
"description": "The number of input tokens used to create the cache entry.",
"minimum": 0,
"title": "Cache Creation Input Tokens",
"type": "integer"
},
"cache_read_input_tokens": {
"default": 0,
"description": "The number of input tokens read from the cache.",
"minimum": 0,
"title": "Cache Read Input Tokens",
"type": "integer"
},
"input_tokens": {
"description": "The number of input tokens which were used.",
"minimum": 0,
"title": "Input Tokens",
"type": "integer"
},
"model": {
"$ref": "#/$defs/Model"
},
"output_tokens": {
"description": "The number of output tokens which were used.",
"minimum": 0,
"title": "Output Tokens",
"type": "integer"
},
"type": {
"const": "message",
"default": "message",
"description": "Usage for a sampling iteration",
"title": "Type",
"type": "string"
}
},
"required": [
"cache_creation",
"cache_creation_input_tokens",
"cache_read_input_tokens",
"input_tokens",
"model",
"output_tokens",
"type"
],
"title": "MessageIterationUsage",
"type": "object"
},
"BetaOutputTokensDetails": {
"properties": {
"thinking_tokens": {
"default": 0,
"description": "Number of output tokens the model generated as internal reasoning, including\nthe thinking-block delimiter tokens.\n\nReflects the raw reasoning the model produced, not the (possibly shorter)\nsummarized thinking text returned in the response body. Computed by\nre-tokenizing the raw reasoning text, so it may differ from the model's exact\ngeneration count by a small number of tokens. Always ≤ `output_tokens`;\n`output_tokens - thinking_tokens` approximates the non-reasoning output.",
"minimum": 0,
"title": "Thinking Tokens",
"type": "integer"
}
},
"required": [
"thinking_tokens"
],
"title": "OutputTokensDetails",
"type": "object"
},
"BetaPlainTextSource": {
"additionalProperties": false,
"properties": {
"data": {
"title": "Data",
"type": "string"
},
"media_type": {
"const": "text/plain",
"title": "Media Type",
"type": "string"
},
"type": {
"const": "text",
"title": "Type",
"type"
# --- truncated at 32 KB (99 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/anthropic/refs/heads/main/json-schema/anthropic-beta-message-schema.json
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.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/anthropic-beta-message"
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.