Retrieve Model - Anthropic Models API Beta Reference
Trust: ★★★☆☆ (0.90) · 0 validations · developer_reference
Published: 2026-05-10 · Source: crawler_authoritative
Tình huống
Anthropic Models API reference for the retrieve method, which retrieves information about a specific model or resolves a model alias to a model ID using the TypeScript SDK.
Insight
The client.beta.models.retrieve(string modelID, ModelRetrieveParams params?, RequestOptions options?) method sends a GET request to /v1/models/{model_id} and returns a BetaModelInfo object. The method accepts a model identifier or alias as the first parameter. Optional params can specify beta version(s) via the betas array, supporting values like ‘message-batches-2024-09-24’, ‘prompt-caching-2024-07-31’, ‘computer-use-2024-10-22’, ‘computer-use-2025-01-24’, ‘pdfs-2024-09-25’, ‘token-counting-2024-11-01’, ‘token-efficient-tools-2025-02-19’, ‘output-128k-2025-02-19’, ‘files-api-2025-04-14’, ‘mcp-client-2025-04-04’, ‘mcp-client-2025-11-20’, ‘dev-full-thinking-2025-05-14’, ‘interleaved-thinking-2025-05-14’, ‘code-execution-2025-05-22’, ‘extended-cache-ttl-2025-04-11’, ‘context-1m-2025-08-07’, ‘context-management-2025-06-27’, ‘model-context-window-exceeded-2025-08-26’, ‘skills-2025-10-02’, ‘fast-mode-2026-02-01’, ‘output-300k-2026-03-24’, ‘user-profiles-2026-03-24’, ‘advisor-tool-2026-03-01’, and ‘managed-agents-2026-04-01’. The returned BetaModelInfo includes: id (unique model identifier), capabilities object with support for batch, citations, code_execution, context_management strategies (clear_thinking_20251015, clear_tool_uses_20250919, compact_20260112), effort levels (high, low, max, medium, xhigh), image_input, pdf_input, structured_outputs, and thinking capability with types (adaptive, enabled). Additional fields include created_at (RFC 3339 datetime), display_name, max_input_tokens, max_tokens, and type set to ‘model’.
Hành động
Call client.beta.models.retrieve() with a model ID string. Optionally pass a ModelRetrieveParams object containing a betas array to specify beta API versions to use. The method returns a promise resolving to BetaModelInfo with model metadata and capability flags. Example usage: const betaModelInfo = await client.beta.models.retrieve('model_id'); followed by accessing betaModelInfo.id. Ensure the Anthropic SDK is installed (@anthropic-ai/sdk) and API key is configured via environment variable ANTHROPIC_API_KEY or constructor option.
Kết quả
Returns a BetaModelInfo object containing the model’s unique identifier, human-readable display name, creation timestamp, token limits (max_input_tokens, max_tokens), type (‘model’), and a capabilities object indicating which features the model supports (batch, citations, code execution, context management strategies, effort levels, image/pdf input, structured outputs, thinking modes).
Điều kiện áp dụng
This is the beta API version of the Models endpoint. Requires @anthropic-ai/sdk package.
Nội dung gốc (Original)
Retrieve
client.beta.models.retrieve(stringmodelID, ModelRetrieveParamsparams?, RequestOptionsoptions?): BetaModelInfo
get /v1/models/{model_id}
Get a specific model.
The Models API response can be used to determine information about a specific model or resolve a model alias to a model ID.
Parameters
-
modelID: stringModel identifier or alias.
-
params: ModelRetrieveParams-
betas?: Array<AnthropicBeta>Optional header to specify the beta version(s) you want to use.
-
(string & {}) -
"message-batches-2024-09-24" | "prompt-caching-2024-07-31" | "computer-use-2024-10-22" | 21 more-
"message-batches-2024-09-24" -
"prompt-caching-2024-07-31" -
"computer-use-2024-10-22" -
"computer-use-2025-01-24" -
"pdfs-2024-09-25" -
"token-counting-2024-11-01" -
"token-efficient-tools-2025-02-19" -
"output-128k-2025-02-19" -
"files-api-2025-04-14" -
"mcp-client-2025-04-04" -
"mcp-client-2025-11-20" -
"dev-full-thinking-2025-05-14" -
"interleaved-thinking-2025-05-14" -
"code-execution-2025-05-22" -
"extended-cache-ttl-2025-04-11" -
"context-1m-2025-08-07" -
"context-management-2025-06-27" -
"model-context-window-exceeded-2025-08-26" -
"skills-2025-10-02" -
"fast-mode-2026-02-01" -
"output-300k-2026-03-24" -
"user-profiles-2026-03-24" -
"advisor-tool-2026-03-01" -
"managed-agents-2026-04-01"
-
-
-
Returns
-
BetaModelInfo-
id: stringUnique model identifier.
-
capabilities: BetaModelCapabilities | nullModel capability information.
-
batch: BetaCapabilitySupportWhether the model supports the Batch API.
-
supported: booleanWhether this capability is supported by the model.
-
-
citations: BetaCapabilitySupportWhether the model supports citation generation.
-
supported: booleanWhether this capability is supported by the model.
-
-
code_execution: BetaCapabilitySupportWhether the model supports code execution tools.
-
supported: booleanWhether this capability is supported by the model.
-
-
context_management: BetaContextManagementCapabilityContext management support and available strategies.
-
clear_thinking_20251015: BetaCapabilitySupport | nullIndicates whether a capability is supported.
-
supported: booleanWhether this capability is supported by the model.
-
-
clear_tool_uses_20250919: BetaCapabilitySupport | nullIndicates whether a capability is supported.
-
supported: booleanWhether this capability is supported by the model.
-
-
compact_20260112: BetaCapabilitySupport | nullIndicates whether a capability is supported.
-
supported: booleanWhether this capability is supported by the model.
-
-
supported: booleanWhether this capability is supported by the model.
-
-
effort: BetaEffortCapabilityEffort (reasoning_effort) support and available levels.
-
high: BetaCapabilitySupportWhether the model supports high effort level.
-
supported: booleanWhether this capability is supported by the model.
-
-
low: BetaCapabilitySupportWhether the model supports low effort level.
-
supported: booleanWhether this capability is supported by the model.
-
-
max: BetaCapabilitySupportWhether the model supports max effort level.
-
supported: booleanWhether this capability is supported by the model.
-
-
medium: BetaCapabilitySupportWhether the model supports medium effort level.
-
supported: booleanWhether this capability is supported by the model.
-
-
supported: booleanWhether this capability is supported by the model.
-
xhigh: BetaCapabilitySupport | nullIndicates whether a capability is supported.
-
supported: booleanWhether this capability is supported by the model.
-
-
-
image_input: BetaCapabilitySupportWhether the model accepts image content blocks.
-
supported: booleanWhether this capability is supported by the model.
-
-
pdf_input: BetaCapabilitySupportWhether the model accepts PDF content blocks.
-
supported: booleanWhether this capability is supported by the model.
-
-
structured_outputs: BetaCapabilitySupportWhether the model supports structured output / JSON mode / strict tool schemas.
-
supported: booleanWhether this capability is supported by the model.
-
-
thinking: BetaThinkingCapabilityThinking capability and supported type configurations.
-
supported: booleanWhether this capability is supported by the model.
-
types: BetaThinkingTypesSupported thinking type configurations.
-
adaptive: BetaCapabilitySupportWhether the model supports thinking with type ‘adaptive’ (auto).
-
supported: booleanWhether this capability is supported by the model.
-
-
enabled: BetaCapabilitySupportWhether the model supports thinking with type ‘enabled’.
-
supported: booleanWhether this capability is supported by the model.
-
-
-
-
-
created_at: stringRFC 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: stringA human-readable name for the model.
-
max_input_tokens: number | nullMaximum input context window size in tokens for this model.
-
max_tokens: number | nullMaximum value for the
max_tokensparameter when using this model. -
type: "model"Object type.
For Models, this is always
"model"."model"
-
Example
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
apiKey: process.env['ANTHROPIC_API_KEY'], // This is the default and can be omitted
});
const betaModelInfo = await client.beta.models.retrieve('model_id');
console.log(betaModelInfo.id);Liên kết
- Nền tảng: Dev Framework · Anthropic
- Nguồn: https://platform.claude.com/docs/en/api/typescript/beta/models/retrieve.md
Xem thêm:
- [[entries/models-retrieve-c-sdk|Models.Retrieve - C# SDK]]
- Retrieve Model - Anthropic Models API
- Files API (Beta) - Ruby SDK Reference
- Create Message - Beta Messages API (Go)
- Create Enrollment URL API Endpoint