# Ability to disable models

**URL:** <https://community.perplexity.ai/t/ability-to-disable-models/5081>\
**Category:** General\
**Tags:** sonar-api\
**Created:** [May 6, 2026, 3:06pm UTC](https://community.perplexity.ai/t/ability-to-disable-models/5081 "2026-05-06T15:06:45Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![indrani\_gajjarapu](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/indrani_gajjarapu/32/3091_2.png) [@indrani\_gajjarapu](https://community.perplexity.ai/u/indrani_gajjarapu)\
**Post date:** [May 6, 2026, 3:06pm UTC](https://community.perplexity.ai/t/ability-to-disable-models/5081/1 "2026-05-06T15:06:45Z")

</div>

Ability to disable models would be a great feature for multiple reasons. Personally, I do not trust OpenAI or Grok - specially when they are planning to have ads in there.

Is this in the pipeline or something that can easily implemented?

---

<div class="post-metadata">

**Author:** ![albert\_pplx](https://avatars.discourse-cdn.com/v4/letter/a/258eb7/32.png) [@albert\_pplx](https://community.perplexity.ai/u/albert_pplx)\
**Post date:** [May 6, 2026, 10:19pm UTC](https://community.perplexity.ai/t/ability-to-disable-models/5081/2 "2026-05-06T22:19:31Z")

</div>

Hey! Thanks for this great question.

You can do this today with the Agent API. It accepts either a [`preset`](https://docs.perplexity.ai/docs/agent-api/presets) or an explicit [`models` array](https://docs.perplexity.ai/docs/agent-api/models), and that array doubles as an [ordered fallback chain](https://docs.perplexity.ai/docs/agent-api/model-fallback) — so if you pass `models=[, "perplexity/sonar", "anthropic/claude-sonnet-4-6"]`, the runtime will only ever try those two, in that order.

One thing to know: presets do route to specific third‑party models by default (for example, `pro-search` defaults to GPT‑5.x under the hood). To enforce your own policy but still keep a preset’s tools and system prompt, you can override the model alongside the preset, e.g.:  
`client.responses.create(preset="pro-search", model="anthropic/claude-sonnet-4-6", input=...)`. The [presets docs](https://docs.perplexity.ai/docs/agent-api/presets) explicitly show that all preset parameters, including `model`, are overrideable.

If you’d rather stay Sonar‑centric, the Agent API also has Sonar‑style options: you can just use a Sonar model ID in `models` (or as `model`) and build your fallback chain around that, or stick to a single Sonar model only. The Agent API is designed as the “multi‑provider” layer for the platform, while the [Sonar API](https://docs.perplexity.ai/docs/sonar/quickstart) is the more focused, web‑grounded chat endpoint.

If you’re migrating from the Sonar API, the shape changes a bit (`messages` → `input`, and search filters/tools move under `tools[...]`), but the mental model is similar and the migration is pretty straightforward. The [Sonar quickstart](https://docs.perplexity.ai/docs/sonar/quickstart) and [Agent API quickstart](https://docs.perplexity.ai/docs/agent-api/quickstart) have concrete examples for both sides if you want to compare them line–by–line.

If you have any further questions, we’d love to answer them and keep the discussion going.

---

<div class="post-metadata">

**Author:** ![NLP](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/nlp/32/2914_2.png) [@NLP](https://community.perplexity.ai/u/NLP)\
**Post date:** [June 18, 2026, 12:44am UTC](https://community.perplexity.ai/t/ability-to-disable-models/5081/3 "2026-06-18T00:44:06Z")

</div>

this can be done with the agent API