---
id: "nr-model-choice-is-becoming-a-runtime-policy-rather-than-a-fixed-dependen-e0347b"
slug: "model-choice-is-becoming-a-runtime-policy-rather-than-a-fixed-dependen-e0347b"
type: "raw_signal"
title: "Model choice is becoming a runtime policy rather than a fixed dependency"
description: "Perplexity is steering workloads through a unified multi-provider Agent API, and NVIDIA’s Switchyard routes LLM traffic across providers while preserving familiar API shapes."
observed_at: "2026-08-21"
record_date: "2026-08-21"
date_kind: "observed_at"
novelty: "notable"
source_platform: "newruntime.com"
topics: []
entities: []
related_patterns: []
source_url: "https://docs.perplexity.ai/docs/agent-api/quickstart"
source_urls: ["https://docs.perplexity.ai/docs/agent-api/quickstart","https://github.com/NVIDIA-NeMo/Switchyard"]
why_it_matters: "Perplexity is steering workloads through a unified multi-provider Agent API, and NVIDIA’s Switchyard routes LLM traffic across providers while preserving familiar API shapes. These approaches make provider selection and routing part of system design, giving builders a way to choose models across workloads without tying the application to one provider."
verification_level: "source-linked"
signal_type: "synthesis"
synthesis_of: [{"slug":"perplexity-moves-sonar-workloads-to-a-multi-provider-agent-api","title":"Perplexity Moves Sonar Workloads to a Multi-Provider Agent API","url":"https://newruntime.com/posts/perplexity-moves-sonar-workloads-to-a-multi-provider-agent-api/"},{"slug":"nvidia-switchyard-makes-model-routing-a-runtime-decision","title":"NVIDIA Switchyard Makes Model Routing a Runtime Decision","url":"https://newruntime.com/posts/nvidia-switchyard-makes-model-routing-a-runtime-decision/"}]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:model-choice-is-becoming-a-runtime-policy-rather-than-a-fixed-dependen-e0347b"
retrieval_nugget: "Perplexity is steering workloads through a unified multi-provider Agent API, and NVIDIA’s Switchyard routes LLM traffic across providers while preserving familiar API shapes. These approaches make provider selection and routing part of system design, giving builders a way to choose models across workloads without tying the application to one provider."
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/model-choice-is-becoming-a-runtime-policy-rather-than-a-fixed-dependen-e0347b/","markdown":"https://newruntime.com/signals/model-choice-is-becoming-a-runtime-policy-rather-than-a-fixed-dependen-e0347b.md","json":"https://newruntime.com/signals/model-choice-is-becoming-a-runtime-policy-rather-than-a-fixed-dependen-e0347b.json"}
---

# Model choice is becoming a runtime policy rather than a fixed dependency

## Retrieval answer

Perplexity is steering workloads through a unified multi-provider Agent API, and NVIDIA’s Switchyard routes LLM traffic across providers while preserving familiar API shapes. These approaches make provider selection and routing part of system design, giving builders a way to choose models across workloads without tying the application to one provider.

Perplexity is steering workloads through a unified multi-provider Agent API, and NVIDIA’s Switchyard routes LLM traffic across providers while preserving familiar API shapes. These approaches make provider selection and routing part of system design, giving builders a way to choose models across workloads without tying the application to one provider.

From the Field Notes:

- [Perplexity Moves Sonar Workloads to a Multi-Provider Agent API](https://newruntime.com/posts/perplexity-moves-sonar-workloads-to-a-multi-provider-agent-api/) (2026-08-21)
- [NVIDIA Switchyard Makes Model Routing a Runtime Decision](https://newruntime.com/posts/nvidia-switchyard-makes-model-routing-a-runtime-decision/) (2026-08-18)

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)