GET
/v1/schemas/anthropic/chat/v1%2Fmessages%3Fbeta%3Dtrue
Accept:
Request body
25 properties · 3 required · 224 $defs| property | type | description | constraints |
|---|---|---|---|
| model* | string | The model that will complete your prompt. | 22 known values |
| messages* | BetaInputMessageUnion[] | Input messages. | |
| max_tokens* | integer | The maximum number of tokens to generate before stopping. | n ≥ 0 |
| billing_policy | BetaBillingPolicy | Declares which organization is billed for the request. | nullable |
| cache_control | BetaCacheControlEphemeral | Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. | nullable |
| compaction | BetaSummarizeCompaction | Compact 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 |
| container | ContainerParams | string | Container identifier for reuse across requests. | nullable |
| context_management | BetaContextManagementConfig | Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. | nullable |
| diagnostics | BetaDiagnosticsParam | Request-level diagnostics. Currently carries the previous response id for prompt-cache divergence reporting. | nullable |
| fallback_credit_token | string | FallbackCreditTokenParam | The `fallback_credit_token` from a prior refusal's `stop_details`. | nullable |
| fallbacks | BetaFallbackConfigV2[] | "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_geo | string | Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. | nullable |
| mcp_servers | BetaRequestMCPServerURLDefinition[] | MCP servers to be utilized in this request | items ≤ 20 |
| metadata | BetaMetadata | An object describing metadata about the request. | |
| output_config | BetaOutputConfig | Configuration options for the model's output, such as the output format. | |
| output_format | BetaJsonOutputFormat | Deprecated: 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_tier | enum | Determines whether to use priority capacity (if available) or standard capacity for this request. | auto | standard_only |
| speed | enum | The 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_sequences | string[] | Custom text sequences that will cause the model to stop generating. | |
| stream | boolean | Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream. | |
| system | string | BetaRequestTextBlock[] | System prompt. | |
| thinking | ThinkingConfigEnabled | ThinkingConfigDi… | Configuration for Claude's thinking. | |
| thread | ThreadCreateParams | 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_choice | ToolChoiceAuto | 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. | |
| tools | BetaToolUnion[] | Definitions of tools that the model may use. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"anthropic","endpointId":"v1/messages?beta=true","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}