> ## Documentation Index > Fetch the complete documentation index at: https://docs.pinecone.io/llms.txt > Use this file to discover all available pages before exploring further. # List the selectable query models > What the `model` field on `POST /query` draws from: the default, every catalog entry, the tier → model-id map, per-phase defaults, and the curate-capable ids. Only entries with `available: true` are selectable; the rest are rejected with `400`. ## OpenAPI ````yaml https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-07/nexus_data_2026-07.oas.yaml get /models openapi: 3.0.3 info: title: Nexus API description: > Nexus turns a set of sources into a queryable, self-improving knowledge base. A context is **sources + a manifest**: upload sources, **curate** them into a searchable index, then query it. The manifest, one validated JSON document, defines how the context indexes, retrieves and answers. Curate is explicit — nothing is queryable until you run it. `{slug}` accepts a context's slug or its UUID. Query with `POST /api/query`, one turn per call, and read the answer from `output[].content[].text`; multi-turn conversations are sessions. Tasks are project-owned at `/api/tasks`, not nested under contexts. contact: name: Pinecone Support url: https://support.pinecone.io email: support@pinecone.io license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0 version: 2026-07 servers: - url: https://{host}/api description: Your Nexus deployment host variables: host: default: api.example.com description: Host of your Nexus deployment. security: - bearerAuth: [] - apiKey: [] tags: - name: Auth description: Login and identity. - name: Project description: The active Pinecone project and its disclosure state. - name: Contexts description: A context is sources + a manifest. Curate it explicitly before querying. - name: Manifest description: Manifest templates and the per-context manifest. - name: Source Files description: >- Per-context source imports (upload, connector, public repo) and the source file tree. - name: Knowledge description: Read-only browse of curated knowledge (chunks + artifacts). - name: Curation description: Curate workflow trigger, curation ledger, and version-pin primitives. - name: Connectors description: >- Project-level links to external source providers (Box, ...). Linked via OAuth or an API key, then used to import source documents into a context. - name: Query description: >- The unified KnowQL Query API: run a query turn (`/query`), fetch a turn (`/queries/{id}`), inspect its trace, manage feedback, comparison flags, and multi-turn sessions (`/sessions`). - name: Tasks description: >- Top-level, project-owned task records for every workflow (optimize, curate, search, work, explore, profile, import, pack, restore, groom). - name: Task Files description: Read, list, and delete files from live or archived task containers. paths: /models: get: tags: - Query summary: List the selectable query models description: >- What the `model` field on `POST /query` draws from: the default, every catalog entry, the tier → model-id map, per-phase defaults, and the curate-capable ids. Only entries with `available: true` are selectable; the rest are rejected with `400`. operationId: list_models parameters: - in: header name: X-Pinecone-Api-Version description: >- Date-based contract version, echoed back on the same header. Omit for the default (`2026-07`); send `unstable` for the in-development surface. An unrecognized value is rejected with `400 unsupported_api_version`. schema: default: 2026-07 x-enum: - 2026-07 - unstable type: string style: simple responses: '200': description: The model catalog content: application/json: schema: $ref: '#/components/schemas/ModelCatalog' components: schemas: ModelCatalog: description: The models this deployment can run, and the defaults it resolves. type: object properties: default: description: Model id used when `model` is omitted type: string models: description: Every catalog entry, selectable or not. type: array items: description: One catalog entry. type: object properties: id: description: >- Catalog model id, passed as `model` on `POST /query`. Some carry a vendor prefix and some do not, so treat it as opaque. type: string label: description: Display name. type: string provider: description: Who serves the model. type: string available: description: >- Whether the model can be selected. An unavailable one is rejected with `400`. type: boolean required: - id - label - provider - available tiers: description: >- Tier (`lite`/`standard`/`pro`) → resolved model id. A tier name is accepted anywhere a model id is, so a caller can ask for `standard` and let the deployment choose. type: object additionalProperties: description: The model id the tier resolves to. type: string phase_defaults: description: Workflow phase → the model id or tier name that phase defaults to. type: object additionalProperties: description: The model id or tier the phase defaults to. type: string supported_curate_models: description: >- Model ids the curate runtime accepts — a subset of the catalog, since curate reads the whole corpus and is priced accordingly. type: array items: description: One entry the curate runtime accepts. type: string query_defaults: description: >- The per-turn harness values a turn runs with when the request sets none. allOf: - $ref: '#/components/schemas/QueryDefaults' required: - default - models - tiers - phase_defaults - supported_curate_models - query_defaults QueryDefaults: description: >- What `max_steps` and `thinking_level` resolve to when `POST /query` omits them. Read these to populate a picker rather than hard-coding the caps. type: object properties: max_steps: description: >- Workflow selector → its agentic tool-loop step cap. Keyed by the same selectors `POST /query` accepts, since each runs a different loop. type: object additionalProperties: description: The step cap that selector runs with. type: integer format: int64 thinking_levels: description: >- Every accepted `thinking_level`, ascending. A value outside this list is rejected with `400`. type: array items: description: One reasoning depth the deployment allows. type: string thinking_level: description: The level a turn runs at when the request omits one. type: string required: - max_steps - thinking_levels - thinking_level securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- Session token from `POST /auth/login`, sent as `Authorization: Bearer `. apiKey: type: apiKey in: header name: Api-Key description: Pinecone API key, accepted as an alternative to the bearer token. ````