# List models — GET /v1/ai/mcp/models URL: https://docs.hanzo.ai/docs/openapi/ai/aimodels > Searches the model catalog — the one GET /v1/models lists — by text, class, family or capability, and answers each match with its class, family, list price (per token and per million; variable for a router billed at the answering model's price), context window and capabilities. `GET /v1/ai/mcp/models` > [AI →](https://docs.hanzo.ai/docs/openapi/ai) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | --------------------------------------- | | **Address** | `https://api.hanzo.ai/v1/ai/mcp/models` | | **Method** | `GET` | | **Operation** | `aiModels` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Searches the model catalog — the one GET /v1/models lists — by text, class, family or capability, and answers each match with its class, family, list price (per token and per million; variable for a router billed at the answering model's price), context window and capabilities. ## Request 5 fields. | Field | In | Type | Required | Description | | ------------ | ----- | ------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | | `q` | query | string | — | Q matches the model's id, name, description or owner, ignoring case. | | `class` | query | string | — | Class keeps one class: premium (third-party frontier models), ours (Hanzo's priced models) or free. | | `family` | query | string | — | Family keeps one Hanzo family: enso, zen, kai or zoo. | | `capability` | query | string | — | Capability keeps the models that have it: tools, vision or reasoning, or a modality they take or give (text, image, audio, file, video, decision). | | `limit` | query | integer | — | Limit is the most models to answer, 1 to 500; 0 answers 50. | ## Response | Status | Body | Meaning | | --------- | --------------- | ------- | | `200` | aiModels | ok | | `default` | problem-details | refused | `200` body — 16 fields. | Field | In | Type | Always | Description | | ------------------------------------- | ---- | --------------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------- | | `models` | body | aiModel\[] | — | Models are the matches, in the catalog's order. | | `models[].capabilities` | body | string\[] | — | Capabilities are tools, vision and reasoning, those the model supports. | | `models[].class` | body | string | — | Class is premium, ours or free. | | `models[].context_window` | body | integer (int64) | — | ContextWindow is the most tokens the model reads at once, absent when the catalog does not say. | | `models[].family` | body | string | — | Family is the Hanzo family (enso, zen, kai, zoo), absent for a third-party model. | | `models[].id` | body | string | — | ID is the model's id, the one a completion or a decision names. | | `models[].inputs` | body | string\[] | — | Inputs are the modalities the model reads. | | `models[].name` | body | string | — | Name is the model's display name. | | `models[].outputs` | body | string\[] | — | Outputs are the modalities the model writes. | | `models[].pricing` | body | aiPrice | — | | | `models[].pricing.completion` | body | string | — | Completion is the price of one output token, a decimal string. | | `models[].pricing.input_per_million` | body | number (double) | — | InputPerMillion is the price of a million input tokens. | | `models[].pricing.output_per_million` | body | number (double) | — | OutputPerMillion is the price of a million output tokens. | | `models[].pricing.prompt` | body | string | — | Prompt is the price of one input token, a decimal string. | | `models[].pricing.variable` | body | boolean | — | Variable is true for a router that bills each answer at the price of the model that gave it; the figures above are then that router's ceiling. | | `total` | body | integer (int64) | — | Total is how many models matched, before Limit. | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** `hanzo` has no subcommand for this operation — the CLI serves only what cloud's live route table confirms. Use HTTP or an SDK. **SDK** **.ts** ```ts import { Configuration, AiApi } from 'hanzoai'; const api = new AiApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.aiModels(); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import AiApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = AiApi(client).ai_models() ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.AiAPI.AiModels(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, ai_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = ai_api::ai_models(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.AiApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new AiApi(client).aiModels(); ``` **HTTP** ```bash curl https://api.hanzo.ai/v1/ai/mcp/models \ -H "Authorization: Bearer $HANZO_API_KEY" ``` **MCP** MCP declares no tool for **ai** — `tools/list` on `https://api.hanzo.ai/v1/mcp` names the products it does reach. Use HTTP or an SDK. --- [AI API](https://docs.hanzo.ai/docs/openapi/ai) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)