Vertex (Anthropic) × WorkDaddy: LLM Provider Integration (2026)

Use Vertex (Anthropic) as the engine behind your WorkDaddy agent team: 12 models available, context windows up to 1M tokens, connected in minutes with your own key.

Vertex (Anthropic) is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the Frontier Labs group. The catalog currently lists 12 models from Vertex (Anthropic): 12 with explicit reasoning, 12 with vision input, and 12 with tool calling — the capability that matters most for agent work. The largest context window reaches 1M tokens.

At a glance

Models available 12
Reasoning models 12
Vision models 12
Tool-calling models 12
Largest context window 1M tokens
API key variable GOOGLE_VERTEX_PROJECT
SDK adapter @ai-sdk/google-vertex/anthropic
Provider docs cloud.google.com ↗

Why run WorkDaddy agents on Vertex (Anthropic) in 2026

Tool calling, context size, and cost decide how well a provider drives an agent team. Vertex (Anthropic) brings 12 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 1M tokens of context at the top end for whole-codebase and long-report work. Because WorkDaddy is model-agnostic, you can route heavy reasoning to Vertex (Anthropic)’s strongest model and bulk work to its cheapest, inside one team.

Best Vertex (Anthropic) models for e-commerce agents (2026)

The current flagships from Vertex (Anthropic) in the WorkDaddy catalog, newest first:

  • Claude Opus 5 — Strongest Claude Opus model for coding, agents, and professional work (1M context)

  • Claude Sonnet 5 — Everyday Claude agent model for coding, planning, browsing, and general work (1M context)

  • Claude Opus 4.8 — Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents (1M context)

  • Claude Opus 4.7 — Stronger Opus tier for advanced software work and high-stakes reasoning (1M context)

  • Claude Sonnet 4.6 — Claude workhorse for coding agents, careful analysis, and production cost control (1M context)

  • Claude Opus 4.6 — High-end Claude for difficult coding, planning, and slower expert reasoning (1M context)

How to connect Vertex (Anthropic) to WorkDaddy

WorkDaddy talks to Vertex (Anthropic) at — via the @ai-sdk/google-vertex/anthropic adapter. Add your credential (typically GOOGLE_VERTEX_PROJECT) in Settings → Models, pick a default model, and every agent can use it immediately — or add Vertex (Anthropic) as one engine among several and let tasks route to the best fit.

Featured models

Model Context Reasoning Released
Claude Opus 5 1M Yes 2026-07-24
Claude Sonnet 5 1M Yes 2026-06-30
Claude Opus 4.8 1M Yes 2026-05-28
Claude Opus 4.7 1M Yes 2026-04-16
Claude Sonnet 4.6 1M Yes 2026-02-17
Claude Opus 4.6 1M Yes 2026-02-05

How it works

01

Connect

In WorkDaddy, open Settings → Models, choose Vertex (Anthropic), and paste your API key (GOOGLE_VERTEX_PROJECT). No key? Start on the managed gateway instead.

02

Put agents to work

Pick Claude Opus 5 or any of the 12 available models as your default — per-agent overrides let you match model to task.

03

Review and approve

Agent output stays draft-first regardless of the model: review diffs and approve actions exactly as before.

Frequently asked questions

Does WorkDaddy support Vertex (Anthropic) in 2026?

Yes — Vertex (Anthropic) is a supported LLM provider with 12 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/google-vertex/anthropic adapter.

How many Vertex (Anthropic) models can I use with WorkDaddy?

12 models are listed for Vertex (Anthropic), including 12 reasoning models and 12 vision-capable models. The flagship lineup above shows the newest.

What context window do Vertex (Anthropic) models offer?

Up to 1M tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.

Is Vertex (Anthropic) the best LLM provider for e-commerce agents?

It depends on the task mix — Vertex (Anthropic) sits in the Frontier Labs group. WorkDaddy is model-agnostic, so the practical answer in 2026 is to combine providers: route each agent task to whichever model fits best.

Put the team to work on your store

Connect your storefront, analytics, and email stack, set a goal, and let the agents run the work end to end. Start on the free plan with your own model key.