Custom Engine pins one exact model. Taskade stops choosing for you on that surface.
Use it when you are comparing models on the same prompt, or when one model genuinely suits a task. For everything else, a rung ages better.
Where to find it
Open the model menu on an agent, a chat, or an automation step.
- In the builder chat, the models sit behind Current Model, under a Custom Engine heading.
- In the agent editor and in automation steps, the same list appears under All Models.
The two menus differ on purpose. An automation step can narrow the list to the models valid for that step, so a step menu can be shorter than the builder menu.
The catalog
Taskade offers 15+ frontier models across every provider in the picker. Speed, intelligence, and cost are relative bands, and they are the same signals the in-app picker shows.
| Model | Provider | Good at | Speed | Intelligence | Cost | Availability |
|---|---|---|---|---|---|---|
| Claude Opus 5 | Anthropic | Maximum reasoning with extended thinking | Slow | Frontier | High | Max and Enterprise |
| Claude Sonnet 5 | Anthropic | Extended thinking for complex tasks | Slow | Frontier | Medium | Every paid plan |
| Claude Haiku 4.5 | Anthropic | Fast, efficient everyday work | Fast | Moderate | Medium | Every paid plan |
| GPT-5.6 Sol | OpenAI | Deepest reasoning for hard problems | Slow | Frontier | High | Max and Enterprise |
| GPT-5.6 Terra | OpenAI | Fast frontier all-rounder | Fast | Frontier | Medium | Business and up |
| GPT-5.6 Luna | OpenAI | Fast, economical quick tasks | Fast | High | Low | Every paid plan |
| Grok 4.6 | xAI | Frontier coding and STEM reasoning | Medium | Frontier | High | Max and Enterprise |
| Grok Build 0.1 | xAI | Fast agentic app building | Fast | High | Medium | Every paid plan |
| Kimi K3 | Moonshot | Long-context agentic reasoning | Slow | Frontier | High | Max and Enterprise |
| Kimi K2.6 | Moonshot | Open-weight generalist | Medium | High | High | Every paid plan |
| Kimi K2.7 Code | Moonshot | Agentic coding | Medium | High | Medium | Every paid plan |
| Qwen 3.7 Max | Alibaba | Agent foundation flagship | Medium | Frontier | Medium | Every paid plan |
| Qwen 3.7 Plus | Alibaba | Cost-effective agentic coding | Fast | High | Medium | Every paid plan |
| MiniMax M3 | MiniMax | Fast open-source generalist | Fast | High | Medium | Every paid plan |
| GLM 5.2 | Z.AI | Autonomous coding | Slow | Frontier | Medium | Max and Enterprise |
| Nemotron 3 Super | NVIDIA | Efficient mixture-of-experts for agents | Fast | High | Medium | Every paid plan |
| DeepSeek V4 Pro | DeepSeek | Frontier reasoning and coding | Fast | High | Low | Every paid plan |
| DeepSeek V4 Flash | DeepSeek | Fast, low-cost everyday work | Fast | Moderate | Low | Every plan, including Free |
This list moves. Treat it as accurate on the date in this page's metadata, not as a contract.Taskade adds frontier models as they ship, and rotates which ones the picker offers. If you want a model you cannot see, ask us. Enterprise agreements can also open models that are not in the default picker, and you can always run a model on your own provider key.
A Custom Engine pick is stored. Your agent, chat, or automation step keeps the exact model id you chose, which is why a pin ages and a rung does not. Nothing breaks when a model leaves this list. Taskade keeps a retired model on file so your saved pick still reads back correctly, and it runs that turn on TSK-Auto instead.
How cost works
The Cost column is a band, not a price. Three things make a single per-model number misleading:
- Request size changes the total. Credits scale with the tokens a step carries. The same model therefore costs more on a large request than on a small one. A few models add a further multiplier above a very large input.
- Rates get re-anchored. Taskade measures real usage after a model launches and adjusts its rate to match.
- Some rates are promotional. A model running on a provider grant costs less than it will once that grant ends.
The model menu shows the current credits for each option at the moment you pick it. That figure is the one to trust. For how metering works, see Model credits.
Context windows
Taskade does not publish a context-window figure per model.
The number a provider advertises describes the raw model, not the budget your step receives. A running step also carries workspace memory, agent knowledge, attachments, and conversation history. The usable remainder therefore differs by surface and by request, and the provider figure overstates what you can pass in.
If a model is not in your picker
The picker rotates, so a model you used last week can be absent today. Nothing breaks when that happens. Taskade routes the turn through TSK-Auto instead, and the work completes on a current model.
If you need a specific model that is not listed, ask us and we can enable it. Enterprise agreements open models outside the default picker. A provider step runs any model on your own key.
This is also why a rung is the better default. A rung follows the catalog forward, and a pin depends on what the picker offers that day.
Run on your own account
To bill a provider account you control, connect it and add a provider step. Taskade supports OpenAI, Anthropic, Google Gemini, Groq, and OpenRouter accounts for this. The step runs on your key, and every step around it keeps working normally.
See Multi-model AI access for the setup.
Next steps
- Read how Taskade picks a model for Auto, rungs, and Infinity Mode.
- See Model credits for metering.