Models

Models

Every prompt, agent, and automation runs on a model. TSK-Auto is the default, and it picks a model on every turn. A manual choice is optional.

This page explains how Taskade picks a model and how to override the pick. For the catalog of models you can pin, see Custom Engine.

Level You choose Best for
TSK-Auto Nothing. Taskade picks for each turn. Almost everything. This is the default.
TSK rungs A speed-to-depth trade-off You know the job is quick, or you know it is hard
Custom Engine One exact model Comparing models, or one model suits the task

TSK-Auto

TSK-Auto is the default on every surface and on every plan. It carries a Recommended pill in the model menu and needs no setup.

Auto picks a model once per turn. It looks at the kind of work in the turn and the plan of the workspace, then picks a model that fits.

Two properties matter more than the specific choice:

  • Auto re-decides every turn. A build turn and a follow-up edit in the same conversation can land on different models.
  • Auto moves to newer models. Taskade updates Auto as models ship and retire, so you get the improvement with no rebuild and no migration.

That second property is why these docs do not name the models behind Auto. A name printed here becomes wrong the next time Taskade updates Auto.

When to override Auto

Override it when you know something about the job that Auto cannot infer from the turn:

You know Use
The job is trivial and you want it now TSK-Instant
The job is a bigger app that needs more care TSK-Thinking
The job is a complex app and worth more credits TSK-Reasoning
You are comparing two models on one prompt Custom Engine

An override applies only to the surface you set it on. Setting a model on one agent changes no other agent.

TSK rungs

A rung sets a trade-off, not a model. You tell Taskade how much thinking the job deserves, and Taskade maps that to a model for you. It is the middle ground between Auto, which decides everything, and Custom Engine, which decides nothing for you.

   TSK-Instant      TSK-Standard     TSK-Thinking     TSK-Reasoning
   ───────────      ────────────     ────────────     ─────────────
   quick edits      everyday apps    bigger apps,     complex apps,
                                     more care        more credits

   ◀───────────────── faster                 deeper ─────────────────▶
Rung What it is for Availability
TSK-Instant Quick edits Every plan, including Free
TSK-Standard Everyday apps Every paid plan
TSK-Thinking Bigger apps that need more care Every paid plan
TSK-Reasoning Complex apps. Uses more credits Business and up

Match the rung to the shape of the work, not to how important the work feels:

  • A one-line change to text that already exists is a TSK-Instant job. A deeper rung returns the same edit more slowly.
  • A normal build step or agent answer is TSK-Standard.
  • A bigger app that needs more care than an everyday build is TSK-Thinking. It uses more credits for each turn than TSK-Standard.
  • Work that produces a complex app or a system rather than an answer is TSK-Reasoning. It uses more credits for each turn than the other rungs.

A rung survives the catalog. When a provider ships a better model at the same trade-off, Taskade moves the rung to it, and your agent improves with no edit. A pinned model id does not move, so it ages.

The rungs are also the whole model menu of an AI step in an automation. That menu shows TSK-Auto and the TSK rungs under a Taskade credits heading, with no Custom Engine list. A step that already stores a pinned model keeps it. If that model is retired, or no longer runs on Taskade AI credits, the step runs on TSK-Auto.

Bring your own key

Taskade can run a model on an API key that you own. There are two paths, and they serve different surfaces.

AI Model Keys. Save a key under Connections → AI Model Keys. Then pick a model from that provider on an agent, or pick a row under Your keys in the agent model menu.

  • On Pro and up, an OpenAI, Anthropic or Google Vertex AI key serves custom agents, Ask Agent, and the AI steps of your automations.
  • On Pro and up, a Google Gemini API key also serves your agents.
  • On Business and up, a key from more providers serves your agents. Examples are xAI, Groq, Mistral, Together AI, OpenRouter, DeepSeek, Azure OpenAI or Cloudflare Workers AI.
  • An xAI, DeepSeek, Z.ai or Alibaba Qwen key also serves an automation AI step whose saved model comes from that provider. The other Business keys serve agents and Taskade EVE only. The model menu of a new automation AI step lists only TSK-Auto and the TSK rungs.
  • On Pro and up, Taskade EVE builds and edits can also run on your key. Taskade EVE takes a key from each provider that your plan allows for agents.
  • Each plan includes a monthly number of agent steps on your key with no Taskade credit fee. Each agent step above that number bills a step fee in Taskade AI credits. Settings → Usage shows the steps that you used and the steps that your plan includes.
  • Each plan also sets a daily cap on agent steps on your key. Past the cap, an agent turn stops with Your workspace used today's agent steps on your own AI key. They come back tomorrow.
  • A Taskade EVE step or an automation AI step on your key bills the step fee from the first step.
  • A visitor who chats with your public agent on your key does not use your included steps, and the visitor pays no fee.

See Bring Your Own AI Keys for the setup, and Claude in Taskade for an agent example. The key providers page lists each provider and the models its key serves.

Provider steps. To bill a provider account you control for one automation step, connect the account and add a provider step. Taskade supports OpenAI, Anthropic, and Google Gemini steps on Pro and up, and Groq and OpenRouter steps on Business and up. The model usage bills your provider account, and each step run bills a step fee in Taskade AI credits. Every step around it keeps working normally. See Multi-model AI access for the provider-step setup.

Next steps

Model routing1

Model families10