submodel × WorkDaddy: LLM Provider Integration (2026)
Use submodel as the engine behind your WorkDaddy agent team: 9 models available, context windows up to 262K tokens, connected in minutes with your own key.
submodel is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the More Providers group. The catalog currently lists 9 models from submodel: 5 with explicit reasoning, 0 with vision input, and 9 with tool calling — the capability that matters most for agent work. The largest context window reaches 262K tokens.
At a glance
| Models available | 9 |
|---|---|
| Reasoning models | 5 |
| Vision models | 0 |
| Tool-calling models | 9 |
| Largest context window | 262K tokens |
| API endpoint | https://llm.submodel.ai/v1 |
| API key variable | SUBMODEL_INSTAGEN_ACCESS_KEY |
| SDK adapter | @ai-sdk/openai-compatible |
| Provider docs | submodel.gitbook.io ↗ |
Why run WorkDaddy agents on submodel in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. submodel brings 9 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 submodel’s strongest model and bulk work to its cheapest, inside one team.
Best submodel models for e-commerce agents (2026)
The current flagships from submodel in the WorkDaddy catalog, newest first:
Qwen3 Coder 480B A35B Instruct — Qwen coding model for software agents, repository edits, and code reasoning (262K context)
Qwen3 235B A22B Instruct 2507 — Qwen instruction model for multilingual chat, reasoning, and tool use (262K context)
Qwen3 235B A22B Thinking 2507 — Qwen reasoning model for deliberate problem solving, math, and coding (262K context)
DeepSeek R1 0528 — DeepSeek reasoning model for multi-step analysis, math, coding, and tools (75K context)
DeepSeek V3 0324 — DeepSeek chat model for instruction following, coding, and analysis (75K context)
DeepSeek V3.1 — DeepSeek chat model for instruction following, coding, and analysis (75K context)
How to connect submodel to WorkDaddy
WorkDaddy talks to submodel at llm.submodel.ai via the @ai-sdk/openai-compatible adapter. Add your credential (typically SUBMODEL_INSTAGEN_ACCESS_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add submodel as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| Qwen3 Coder 480B A35B Instruct | 262K | No | 2025-08-23 |
| Qwen3 235B A22B Instruct 2507 | 262K | No | 2025-08-23 |
| Qwen3 235B A22B Thinking 2507 | 262K | Yes | 2025-08-23 |
| DeepSeek R1 0528 | 75K | Yes | 2025-08-23 |
| DeepSeek V3 0324 | 75K | No | 2025-08-23 |
| DeepSeek V3.1 | 75K | Yes | 2025-08-23 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose submodel, and paste your API key (SUBMODEL_INSTAGEN_ACCESS_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick Qwen3 Coder 480B A35B Instruct or any of the 9 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 submodel in 2026?
Yes — submodel is a supported LLM provider with 9 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/openai-compatible adapter.
How many submodel models can I use with WorkDaddy?
9 models are listed for submodel, including 5 reasoning models and 0 vision-capable models. The flagship lineup above shows the newest.
What context window do submodel models offer?
Up to 262K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is submodel the best LLM provider for e-commerce agents?
It depends on the task mix — submodel 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.