Thinking Machines × WorkDaddy: LLM Provider Integration (2026)
Use Thinking Machines as the engine behind your WorkDaddy agent team: 2 models available, context windows up to 262K tokens, connected in minutes with your own key.
Thinking Machines is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the More Providers group. The catalog currently lists 2 models from Thinking Machines: 2 with explicit reasoning, 2 with vision input, and 2 with tool calling — the capability that matters most for agent work. The largest context window reaches 262K tokens.
At a glance
| Models available | 2 |
|---|---|
| Reasoning models | 2 |
| Vision models | 2 |
| Tool-calling models | 2 |
| Largest context window | 262K tokens |
| API endpoint | https://tinker.thinkingmachines.dev/services/tinker-prod/anthropic/api/v1 |
| API key variable | TINKER_API_KEY |
| SDK adapter | @ai-sdk/anthropic |
| Provider docs | tinker-docs.thinkingmachines.ai ↗ |
Why run WorkDaddy agents on Thinking Machines in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. Thinking Machines brings 2 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 Thinking Machines’s strongest model and bulk work to its cheapest, inside one team.
Best Thinking Machines models for e-commerce agents (2026)
The current flagships from Thinking Machines in the WorkDaddy catalog, newest first:
Inkling (256K) — Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio (262K context)
Inkling — Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio (66K context)
How to connect Thinking Machines to WorkDaddy
WorkDaddy talks to Thinking Machines at tinker.thinkingmachines.dev via the @ai-sdk/anthropic adapter. Add your credential (typically TINKER_API_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add Thinking Machines as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| Inkling (256K) | 262K | Yes | 2026-07-15 |
| Inkling | 66K | Yes | 2026-07-15 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose Thinking Machines, and paste your API key (TINKER_API_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick Inkling (256K) or any of the 2 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 Thinking Machines in 2026?
Yes — Thinking Machines is a supported LLM provider with 2 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/anthropic adapter.
How many Thinking Machines models can I use with WorkDaddy?
2 models are listed for Thinking Machines, including 2 reasoning models and 2 vision-capable models. The flagship lineup above shows the newest.
What context window do Thinking Machines models offer?
Up to 262K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is Thinking Machines the best LLM provider for e-commerce agents?
It depends on the task mix — Thinking Machines 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.