> For the complete documentation index, see [llms.txt](https://docs.vapinetwork.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.vapinetwork.ai/router/models.md). # Models Router is coming soon; its source catalog has 150 configured model rows across five kinds, without verified launch availability. {% hint style="info" %} vAPI Router is coming soon. This page describes how it works at launch. {% endhint %} Router is coming soon. Its source catalog contains 150 configured rows across five model kinds; these counts do not establish deployed model availability. ## Catalog policy The catalog is a policy, not a fixed allowlist. Hosted Venice types are included when they meet Router's routing and metering rules. A model Venice adds to a hosted type can appear on the next catalog regeneration without an id being added to a Router file. | Kind | Venice type | Catalog count | Metering unit | Example model id | | ------------- | ----------- | ------------: | ---------------- | -------------------------------- | | Text | `text` | 101 | Per token | `venice/deepseek-v3.2` | | Embedding | `embedding` | 9 | Per token | `venice/text-embedding-bge-m3` | | Speech | `tts` | 11 | Per character | `venice/tts-kokoro` | | Transcription | `asr` | 5 | Per audio second | `venice/openai/whisper-large-v3` | | Image | `image` | 24 | Per image | `venice/venice-sd35` | The source catalog contains 150 configured rows. Counts can change with the upstream catalog or routing policy; they are not a live availability guarantee. ## Held-back entries The catalog holds back entries when Router cannot route or meter them through the OpenAI-compatible surface: * `e2ee-*` text variants require client-side encryption that an OpenAI SDK cannot perform. * `heretic`, `uncensored`, and `lustify` ids, plus models with an `uncensored` trait, are held back by product policy. * `gpt-image*` ids use LiteLLM's token-based image calculator instead of a flat per-image unit. * `bria-bg-remover` is an image-to-image tool, not a `POST /images/generations` model. * Offline models and models without the metering data required for their kind are dropped. Whole Venice types are also excluded when they use custom endpoints that Router cannot route and meter through its OpenAI-compatible surface. These include `video`, `music`, `inpaint`, `upscale`, and `decision`. ## List models at launch At launch, the vAPI management API will expose its catalog at: ```http GET /api/router/models ``` The OpenAI-compatible model listing requires a Router key. An unauthenticated request returned HTTP 401 in the 2026-10-02 audit. At launch, the route is: ```http GET /v1/models ``` See [Call your first model](/router/api-quickstart.md) for an authenticated request example. Checked on 2026-10-02. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.vapinetwork.ai/router/models.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.