STACKIT × WorkDaddy: LLM Provider Integration (2026)
Use STACKIT as the engine behind your WorkDaddy agent team: 8 models available, context windows up to 262K tokens, connected in minutes with your own key.
STACKIT is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the More Providers group. The catalog currently lists 8 models from STACKIT: 2 with explicit reasoning, 3 with vision input, and 5 with tool calling — the capability that matters most for agent work. The largest context window reaches 262K tokens.
At a glance
| Models available | 8 |
|---|---|
| Reasoning models | 2 |
| Vision models | 3 |
| Tool-calling models | 5 |
| Largest context window | 262K tokens |
| API endpoint | https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1 |
| API key variable | STACKIT_API_KEY |
| SDK adapter | @ai-sdk/openai-compatible |
| Provider docs | docs.stackit.cloud ↗ |
Why run WorkDaddy agents on STACKIT in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. STACKIT brings 5 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 262K 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 STACKIT’s strongest model and bulk work to its cheapest, inside one team.
Best STACKIT models for e-commerce agents (2026)
The current flagships from STACKIT in the WorkDaddy catalog, newest first:
Qwen3.6 27B — Qwen vision-language model for visual reasoning, documents, and agent tasks (262K context)
Qwen3-VL Embedding 8B — Embedding model for semantic search, retrieval, clustering, and ranking pipelines (32K context)
GPT OSS 20B — Open GPT reasoning model for self-hosted agents and controllable deployments (131K context)
GPT OSS 120B — Open GPT reasoning model for self-hosted agents and controllable deployments (131K context)
Gemma 3 27B — Open Gemma instruction model for efficient chat and self-hosted deployments (37K context)
Llama 3.3 70B — Open Llama instruction model for multilingual chat, reasoning, and coding (128K context)
How to connect STACKIT to WorkDaddy
WorkDaddy talks to STACKIT at api.openai-compat.model-serving.eu01.onstackit.cloud via the @ai-sdk/openai-compatible adapter. Add your credential (typically STACKIT_API_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add STACKIT as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| Qwen3.6 27B | 262K | No | 2026-04-22 |
| Qwen3-VL Embedding 8B | 32K | No | 2026-02-05 |
| GPT OSS 20B | 131K | Yes | 2025-08-05 |
| GPT OSS 120B | 131K | Yes | 2025-08-05 |
| Gemma 3 27B | 37K | No | 2025-05-17 |
| Llama 3.3 70B | 128K | No | 2024-12-05 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose STACKIT, and paste your API key (STACKIT_API_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick Qwen3.6 27B or any of the 8 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 STACKIT in 2026?
Yes — STACKIT is a supported LLM provider with 8 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/openai-compatible adapter.
How many STACKIT models can I use with WorkDaddy?
8 models are listed for STACKIT, including 2 reasoning models and 3 vision-capable models. The flagship lineup above shows the newest.
What context window do STACKIT models offer?
Up to 262K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is STACKIT the best LLM provider for e-commerce agents?
It depends on the task mix — STACKIT sits in the More Providers group. WorkDaddy is model-agnostic, so the practical answer in 2026 is to combine providers: route each agent task to whichever model fits best.
Keep reading
Pioneer
More Providers
Cortecs
More Providers
CrossModel
More Providers
EmpirioLabs AI
More Providers
Explore more integration directories
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.