GET

/v1/schemas/anthropic/chat/v1%2Fmessages%3Fbeta%3Dtrue

kind inputactivity chathash 4003ede5…extracted Nov 21, 2026version currentsource upstream spec ↗

Request body

25 properties · 3 required · 224 $defs
propertytypedescriptionconstraints
model*stringThe model that will complete your prompt.22 known values
messages*BetaInputMessageUnion[]Input messages.
max_tokens*integerThe maximum number of tokens to generate before stopping.n ≥ 0
billing_policyBetaBillingPolicyDeclares which organization is billed for the request.nullable
cache_controlBetaCacheControlEphemeralTop-level cache control automatically applies a cache_control marker to the last cacheable block in the request.nullable
compactionBetaSummarizeCompactionCompact the whole conversation and return a signed `compaction` block, alone, that a later request sends back first in `messages`, in place of the messages it summarizes. There is no trigger and no pause flag: sending the parameter compacts, and nothing is sam…nullable
containerContainerParams | stringContainer identifier for reuse across requests.nullable
context_managementBetaContextManagementConfigContext management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not.nullable
diagnosticsBetaDiagnosticsParamRequest-level diagnostics. Currently carries the previous response id for prompt-cache divergence reporting.nullable
fallback_credit_tokenstring | FallbackCreditTokenParamThe `fallback_credit_token` from a prior refusal's `stop_details`.nullable
fallbacksBetaFallbackConfigV2[] | "default"Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. Some models don't support fallbacks; on those models, a list of fa…nullable
inference_geostringSpecifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used.nullable
mcp_serversBetaRequestMCPServerURLDefinition[]MCP servers to be utilized in this requestitems ≤ 20
metadataBetaMetadataAn object describing metadata about the request.
output_configBetaOutputConfigConfiguration options for the model's output, such as the output format.
output_formatBetaJsonOutputFormatDeprecated: Use `output_config.format` instead. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) A schema to specify Claude's output format in responses. This parameter will be removed in a future release.nullable · deprecated
service_tierenumDetermines whether to use priority capacity (if available) or standard capacity for this request.auto | standard_only
speedenumThe inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference. Some models require the `fast-mode-2026-02-01` beta header for any `speed` value. See [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for which models.standard | fast · nullable
stop_sequencesstring[]Custom text sequences that will cause the model to stop generating.
streambooleanWhether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream.
systemstring | BetaRequestTextBlock[]System prompt.
thinkingThinkingConfigEnabled | ThinkingConfigDi…Configuration for Claude's thinking.
threadThreadCreateParams | ThreadContinueParam…Server-held conversation state (a Thread). `{"type": "create"}` asks the server to hold this conversation's state under the response's `id`; `{"type": "continue", "previous_message_id": ...}` resumes from a previous response so only the new turn's messages are sent. The response shape is unchanged.nullable
tool_choiceToolChoiceAuto | ToolChoiceAny | ToolCho…How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
toolsBetaToolUnion[]Definitions of tools that the model may use.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"anthropic","endpointId":"v1/messages?beta=true","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}