SAP AI Core × WorkDaddy: LLM Provider Integration (2026)
Use SAP AI Core as the engine behind your WorkDaddy agent team: 43 models available, context windows up to 1.1M tokens, connected in minutes with your own key.
SAP AI Core is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the Enterprise Data Platforms group. The catalog currently lists 43 models from SAP AI Core: 25 with explicit reasoning, 33 with vision input, and 35 with tool calling — the capability that matters most for agent work. The largest context window reaches 1.1M tokens.
At a glance
| Models available | 43 |
|---|---|
| Reasoning models | 25 |
| Vision models | 33 |
| Tool-calling models | 35 |
| Largest context window | 1.1M tokens |
| API key variable | AICORE_SERVICE_KEY |
| SDK adapter | @jerome-benoit/sap-ai-provider-v2 |
| Provider docs | help.sap.com ↗ |
Why run WorkDaddy agents on SAP AI Core in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. SAP AI Core brings 35 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 1.1M 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 SAP AI Core’s strongest model and bulk work to its cheapest, inside one team.
Best SAP AI Core models for e-commerce agents (2026)
The current flagships from SAP AI Core in the WorkDaddy catalog, newest first:
anthropic--claude-4.8-opus — Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents (1M context)
gemini-3.5-flash — Fast Gemini model balancing multimodal reasoning, tool use, and cost (1M context)
gemini-3.1-flash-lite — Low-latency Gemini model for high-volume multimodal and agent workloads (1M context)
gpt-5.5 — Frontier GPT model for professional reasoning, coding, and multimodal work (1.1M context)
anthropic--claude-4.7-opus — Flagship Claude model for deep reasoning, coding, and long-horizon agents (1M context)
mistralai--mistral-small — Fast Mistral production model for chat, extraction, and cost-sensitive agents (128K context)
How to connect SAP AI Core to WorkDaddy
WorkDaddy talks to SAP AI Core at — via the @jerome-benoit/sap-ai-provider-v2 adapter. Add your credential (typically AICORE_SERVICE_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add SAP AI Core as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| anthropic--claude-4.8-opus | 1M | Yes | 2026-05-28 |
| gemini-3.5-flash | 1M | Yes | 2026-05-19 |
| gemini-3.1-flash-lite | 1M | Yes | 2026-05-07 |
| gpt-5.5 | 1.1M | Yes | 2026-04-23 |
| anthropic--claude-4.7-opus | 1M | Yes | 2026-04-16 |
| mistralai--mistral-small | 128K | Yes | 2026-03-16 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose SAP AI Core, and paste your API key (AICORE_SERVICE_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick anthropic--claude-4.8-opus or any of the 43 available models as your default — per-agent overrides let you match model to task.
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 SAP AI Core in 2026?
Yes — SAP AI Core is a supported LLM provider with 43 models in the WorkDaddy catalog, connected with your own API key via the @jerome-benoit/sap-ai-provider-v2 adapter.
How many SAP AI Core models can I use with WorkDaddy?
43 models are listed for SAP AI Core, including 25 reasoning models and 33 vision-capable models. The flagship lineup above shows the newest.
What context window do SAP AI Core models offer?
Up to 1.1M tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is SAP AI Core the best LLM provider for e-commerce agents?
It depends on the task mix — SAP AI Core sits in the Enterprise Data Platforms 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.