读取模型

GET /openai/v1/models/{model}● 支持

OpenAI 官方文档 ↗

请求参数

modelstring必填
path: Model ID from GET /openai/v1/models, including any publisher prefix.

200 model

返回与列表中同一条目相同的模型对象。只有声明了 OpenAI 协议的模型可见；模型 ID 可以带斜杠分隔的发布方前缀。不存在或没有声明 OpenAI 协议的模型返回 404。

错误按 OpenAI 格式返回，参见错误码

响应

HTTP 200

The matching OpenRouter model list entry.

application/json

名称	类型	说明
alias_target	object	Concrete model targeted by this tilde-latest alias, when applicable
alias_target.name	string	Human-readable name of the concrete model targeted by this alias
alias_target.slug	string	Routable model ID of the concrete target, matching that model row's id
architecture	object	Model architecture information
architecture.input_modalities	array<string>	Supported input modalities
architecture.instruct_type	string \| null	Instruction format type
architecture.modality	string \| null	Primary modality of the model
architecture.output_modalities	array<string>	Supported output modalities
architecture.tokenizer	string	Tokenizer type used by the model
benchmarks	object	Third-party benchmark rankings for this model. Omitted when no benchmark data is available.
benchmarks.artificial_analysis	object	Artificial Analysis benchmark index scores.
benchmarks.design_arena	array<object>	Design Arena ELO rankings across arena+category pairs.
canonical_slug	string	Canonical slug for the model
context_length	integer \| null	Maximum context length in tokens
created	integer	Unix timestamp of when the model was created
default_parameters	object \| null	Default parameters for this model
default_parameters.frequency_penalty	number \| null
default_parameters.presence_penalty	number \| null
default_parameters.repetition_penalty	number \| null
default_parameters.temperature	number \| null
default_parameters.top_k	integer \| null
default_parameters.top_p	number \| null
description	string	Description of the model
expiration_date	string \| null	The date after which the model may be removed. ISO 8601 date string (YYYY-MM-DD) or null if no expiration.
hugging_face_id	string \| null	Hugging Face model identifier, if applicable
id	string	Unique identifier for the model
knowledge_cutoff	string \| null	The date up to which the model was trained on data. ISO 8601 date string (YYYY-MM-DD) or null if unknown.
links	object	Related API endpoints and resources for this model.
links.details	string	URL for the model details/endpoints API
name	string	Display name of the model
per_request_limits	object \| null	Per-request token limits
per_request_limits.completion_tokens	number	Maximum completion tokens per request
per_request_limits.prompt_tokens	number	Maximum prompt tokens per request
pricing	object	Pricing information for the model
pricing.audio	string	Price in USD per audio input token
pricing.audio_output	string	Price in USD per audio output token
pricing.completion	string	Price in USD per token for completion (output) generation
pricing.discount	number	Fractional discount applied to this endpoint's pricing; the price is multiplied by (1 - discount) (0 = no discount, 1 = free)
pricing.image	string	Price in USD per image; present only for a flat registry price
pricing.image_output	string	Price in USD per output image
pricing.image_token	string	Price in USD per image token
pricing.input_audio_cache	string	Price in USD per cached audio input token
pricing.input_cache_read	string	Price in USD per cached input token (read)
pricing.input_cache_write	string	Price per cache-write token, in USD per token. For providers with multiple cache TTLs (e.g. Anthropic), this is the default (5-minute) cache-write rate.
pricing.input_cache_write_1h	string	Price per 1-hour cache-write token, in USD per token. Only present for providers that price an extended (1-hour) cache TTL separately, such as Anthropic.
pricing.internal_reasoning	string	Price in USD per internal reasoning token
pricing.overrides	array<object>	Conditional overrides of the base pricing (e.g. long-context or time-based pricing). An entry applies when all of its condition fields (e.g. min_prompt_tokens, or the utc_start/utc_end time window) match the request; among applicable entries, later entries win per key; price keys absent from an entry inherit the base price. The top-level pricing keys always reflect the price that applies under default conditions.
pricing.prompt	string	Price in USD per token for prompt (input) processing
pricing.request	string	Price in USD per request
pricing.web_search	string	Price in USD per web search
pricing.video_second	string	Praxis extension: USD per second of output video.
pricing.audio_input_minute	string	Praxis extension: USD per minute of input audio.
pricing.audio_output_minute	string	Praxis extension: USD per minute of output audio.
pricing.input_character	string	Praxis extension: USD per input character.
pricing.page	string	Praxis extension: USD per OCR page.
reasoning	object	Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models.
reasoning.default_effort	string \| null	Default reasoning effort when the client enables reasoning without specifying effort. Maps to `reasoning.effort` in chat requests. When `"none"`, prefer omitting effort unless the user explicitly disables reasoning.
reasoning.default_enabled	boolean	Default reasoning enabled state when the client does not set `reasoning.enabled`.
reasoning.mandatory	boolean	When true, reasoning cannot be disabled and effort "none" is rejected.
reasoning.supported_efforts	array \| null	Allowed reasoning effort values for this model, in descending effort order (highest first). Null means no allowlist — all gateway effort values are accepted.
reasoning.supports_max_tokens	boolean	Present and `true` when the model accepts `reasoning.max_tokens` in requests (Anthropic-style) instead of or in addition to `reasoning.effort`. Omitted otherwise.
supported_parameters	array<string>	List of supported parameters for this model
supported_voices	array \| null	List of supported voice identifiers for TTS models. Null for non-TTS models.
top_provider	object	Information about the top provider for this model
top_provider.context_length	integer \| null	Context length from the top provider
top_provider.is_moderated	boolean	Whether the top provider moderates content
top_provider.max_completion_tokens	integer \| null	Maximum completion tokens from the top provider. Input and output tokens share the context window, so the effective maximum output for a request is further limited by the context remaining after input tokens.