GitLab Duo × WorkDaddy: LLM Provider Integration (2026)
Use GitLab Duo as the engine behind your WorkDaddy agent team: 23 models available, context windows up to 1.1M tokens, connected in minutes with your own key.
GitLab Duo is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the Coding & IDE group. The catalog currently lists 23 models from GitLab Duo: 23 with explicit reasoning, 23 with vision input, and 23 with tool calling — the capability that matters most for agent work. The largest context window reaches 1.1M tokens.
At a glance
| Models available | 23 |
|---|---|
| Reasoning models | 23 |
| Vision models | 23 |
| Tool-calling models | 23 |
| Largest context window | 1.1M tokens |
| API key variable | GITLAB_TOKEN |
| SDK adapter | gitlab-ai-provider |
| Provider docs | docs.gitlab.com ↗ |
Why run WorkDaddy agents on GitLab Duo in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. GitLab Duo brings 23 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 GitLab Duo’s strongest model and bulk work to its cheapest, inside one team.
Best GitLab Duo models for e-commerce agents (2026)
The current flagships from GitLab Duo in the WorkDaddy catalog, newest first:
Agentic Chat (Claude Opus 5) — Strongest Claude Opus model for coding, agents, and professional work (1M context)
Agentic Chat (GPT-5.6 Terra) — Balanced GPT-5.6 model for capable, cost-efficient everyday work (1.1M context)
Agentic Chat (GPT-5.6 Luna) — Cost-efficient GPT-5.6 model for fast, high-volume workloads (1.1M context)
Agentic Chat (GPT-5.6 Sol) — Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows (1.1M context)
Agentic Chat (Claude Sonnet 5) — Everyday Claude agent model for coding, planning, browsing, and general work (1M context)
Agentic Chat (Claude Fable 5) — Claude model for creative writing, analysis, and controlled agent workflows (1M context)
How to connect GitLab Duo to WorkDaddy
WorkDaddy talks to GitLab Duo at — via the gitlab-ai-provider adapter. Add your credential (typically GITLAB_TOKEN) in Settings → Models, pick a default model, and every agent can use it immediately — or add GitLab Duo as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| Agentic Chat (Claude Opus 5) | 1M | Yes | 2026-07-24 |
| Agentic Chat (GPT-5.6 Terra) | 1.1M | Yes | 2026-07-09 |
| Agentic Chat (GPT-5.6 Luna) | 1.1M | Yes | 2026-07-09 |
| Agentic Chat (GPT-5.6 Sol) | 1.1M | Yes | 2026-07-09 |
| Agentic Chat (Claude Sonnet 5) | 1M | Yes | 2026-06-30 |
| Agentic Chat (Claude Fable 5) | 1M | Yes | 2026-06-09 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose GitLab Duo, and paste your API key (GITLAB_TOKEN). No key? Start on the managed gateway instead.
Put agents to work
Pick Agentic Chat (Claude Opus 5) or any of the 23 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 GitLab Duo in 2026?
Yes — GitLab Duo is a supported LLM provider with 23 models in the WorkDaddy catalog, connected with your own API key via the gitlab-ai-provider adapter.
How many GitLab Duo models can I use with WorkDaddy?
23 models are listed for GitLab Duo, including 23 reasoning models and 23 vision-capable models. The flagship lineup above shows the newest.
What context window do GitLab Duo models offer?
Up to 1.1M tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is GitLab Duo the best LLM provider for e-commerce agents?
It depends on the task mix — GitLab Duo sits in the Coding & IDE 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
GitHub Models
Coding & IDE
GitHub Copilot
Coding & IDE
ClinePass
Coding & IDE
Umans AI Coding Plan
Coding & IDE
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.