Atomic Chat × WorkDaddy: LLM Provider Integration (2026)
Use Atomic Chat as the engine behind your WorkDaddy agent team: 5 models available, context windows up to 131K tokens, connected in minutes with your own key.
Atomic Chat is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the Local & Private group. The catalog currently lists 5 models from Atomic Chat: 0 with explicit reasoning, 2 with vision input, and 3 with tool calling — the capability that matters most for agent work. The largest context window reaches 131K tokens.
At a glance
| Models available | 5 |
|---|---|
| Reasoning models | 0 |
| Vision models | 2 |
| Tool-calling models | 3 |
| Largest context window | 131K tokens |
| API endpoint | http://127.0.0.1:1337/v1 |
| API key variable | ATOMIC_CHAT_API_KEY |
| SDK adapter | @ai-sdk/openai-compatible |
| Provider docs | atomic.chat ↗ |
Why run WorkDaddy agents on Atomic Chat in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. Atomic Chat brings 3 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 131K 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 Atomic Chat’s strongest model and bulk work to its cheapest, inside one team.
Best Atomic Chat models for e-commerce agents (2026)
The current flagships from Atomic Chat in the WorkDaddy catalog, newest first:
Gemma 4 E4B Instruct (IQ4_XS) — Open Gemma instruction model for efficient chat and self-hosted deployments (33K context)
Gemma 4 E4B Instruct (MLX 4-bit) — Open Gemma instruction model for efficient chat and self-hosted deployments (33K context)
Qwen 3.5 9B (Q4_K_M) — Qwen vision-language model for visual reasoning, documents, and agent tasks (33K context)
Qwen 3.5 9B (MLX 4-bit) — Qwen vision-language model for visual reasoning, documents, and agent tasks (33K context)
Meta Llama 3.1 8B Instruct (GGUF) — Open Llama instruction model for multilingual chat, reasoning, and coding (131K context)
How to connect Atomic Chat to WorkDaddy
WorkDaddy talks to Atomic Chat at 127.0.0.1 via the @ai-sdk/openai-compatible adapter. Add your credential (typically ATOMIC_CHAT_API_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add Atomic Chat as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| Gemma 4 E4B Instruct (IQ4_XS) | 33K | No | 2026-04-02 |
| Gemma 4 E4B Instruct (MLX 4-bit) | 33K | No | 2026-04-02 |
| Qwen 3.5 9B (Q4_K_M) | 33K | No | 2026-03-05 |
| Qwen 3.5 9B (MLX 4-bit) | 33K | No | 2026-03-05 |
| Meta Llama 3.1 8B Instruct (GGUF) | 131K | No | 2024-07-23 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose Atomic Chat, and paste your API key (ATOMIC_CHAT_API_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick Gemma 4 E4B Instruct (IQ4_XS) or any of the 5 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 Atomic Chat in 2026?
Yes — Atomic Chat is a supported LLM provider with 5 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/openai-compatible adapter.
How many Atomic Chat models can I use with WorkDaddy?
5 models are listed for Atomic Chat, including 0 reasoning models and 2 vision-capable models. The flagship lineup above shows the newest.
What context window do Atomic Chat models offer?
Up to 131K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is Atomic Chat the best LLM provider for e-commerce agents?
It depends on the task mix — Atomic Chat sits in the Local & Private 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
Ollama Cloud
Local & Private
Tinfoil
Local & Private
Privatemode AI
Local & Private
LMStudio
Local & Private
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.