Sistava

Choose AI Models

The AI Model page lets you see every model available on the platform and set the model every employee in your workspace runs on.

TL;DR

Go to Settings > Technical > AI Model to browse all available models organized by tier (Fast, Standard, Advanced, Frontier). The model you pick here is what every employee uses, workspace-wide. The tier is a rough capability class, and credit cost per message varies by the specific model you choose.

Where to Find It

  1. Click the gear icon in the top-right of your workspace
  2. Go to Technical > AI Model

Model Tiers

Every model belongs to one of four tiers. The tier is a capability class, not a strict price ladder: a Fast model and an Advanced model can land close in credit cost, so check the exact rate on the model you pick.

Tier Capability Typical Use
Fast Good for simple, well-defined work Quick lookups, formatting, simple drafts, routine Q&A
Standard Handles most everyday tasks well Conversations, analysis, writing, planning
Advanced Strong reasoning and nuance Complex analysis, long documents, multi-step reasoning
Frontier The top-of-line brains The hardest work, where quality matters most

Available Models

Fast Tier

Model Provider Credits per 1M tokens
GPT-5 Nano OpenAI 33
GPT-4.1 Nano OpenAI 40
GPT-4o Mini OpenAI 61
GPT-4.1 Mini OpenAI 162
GPT-5.4 Nano OpenAI 110
GPT-5 Mini OpenAI 165
Gemini 3.1 Flash Lite Google 365

Standard Tier

Model Provider Credits per 1M tokens
DeepSeek V4 Flash DigitalOcean 98
Llama 4 Maverick Parasail 222
Kimi K2.5 DeepInfra 230
MiniMax M2.7 DeepInfra 267
Qwen3 Coder DeepInfra 406
GPT-5.4 Mini OpenAI 399
Kimi K2.6 DeepInfra 421
o4 Mini OpenAI 445
Haiku 4.5 Anthropic 468
GPT-5.6 Luna OpenAI 872
Grok 4.3 xAI 950
GPT-4o OpenAI 1,011
Gemini 3.5 Flash Google 2,193

Advanced Tier

Model Provider Credits per 1M tokens Notes
Qwen3 235B Thinking Alibaba 325 Open reasoning
MiniMax M3 MiniMax 333
DeepSeek V4 Pro DeepSeek 588
DeepSeek R1 SiliconFlow 582 Reasoning flagship
GPT-5.1 OpenAI 824
GLM 5.2 DeepInfra 907 Long-horizon tasks, 1M context
GPT-5.2 OpenAI 1,154
Sonnet 4.6 Anthropic 1,404
Sonnet 4.5 Anthropic 1,404 Prior Sonnet
Sonnet 5 Anthropic 1,404 Latest Sonnet
Grok 4.5 xAI 1,871 Latest Grok flagship
GPT-5.4 OpenAI 2,181
GPT-5.6 Terra OpenAI 2,181 Mid GPT-5.6
Gemini 3.1 Pro Google 4,795 Latest Gemini Pro, large-context rate

Frontier Tier

The top-of-line brains. Paid plans use one automatically as their starting model.

Model Provider Credits per 1M tokens Notes
Kimi K3 Moonshot AI 3,860 Recommended. The default brain for paid plans
Opus 4.8 Anthropic 2,340 Latest Opus
Opus 4.5 Anthropic 2,340 Prior Opus generation
Opus 4.7 Anthropic 2,340 Prior Opus generation
Opus 4.6 Anthropic 2,340 Prior Opus generation
Opus 4.1 Anthropic 7,021 Legacy Opus (old $15/$75 pricing)
Fable 5 Anthropic 4,681 Premium creative-tier brain
GPT-5.5 OpenAI 4,362 Latest OpenAI flagship
GPT-5.6 Sol OpenAI 4,362 Flagship GPT-5.6
GPT-5.2 Pro OpenAI 13,851 Premium
GPT-5.4 Pro OpenAI 26,170 Premium
GPT-5.5 Pro OpenAI 26,170 Latest OpenAI Pro, premium

What You See on the Page

The AI Model page displays all available models grouped by tier in the Employee Brain card. For each model you can see:

You can also sort the list by cheapest, by provider, or by reasoning strength instead of by tier, and filter to reasoning-only models.

Setting the Model

The model you pick here is what every employee in your workspace uses. There is currently no per-employee override in the interface: model, thinking depth, and per-turn action limit are controlled workspace-wide only, to keep one place in sync instead of two.

  1. Go to Settings > Technical > AI Model
  2. In the Employee Brain card, pick the model you want
  3. The change saves automatically and takes effect on each employee's next turn

Free and Starter plans stay on the platform default and cannot pick a different model; the picker shows every model with a lock icon and an upgrade prompt. Builder plan and above can choose freely.

Reasoning Models

Some models stream a visible thinking process, shown as a "thinking" phase in the chat before the final answer. Reasoning capability is rated with stars (1 to 5) rather than a fixed on/off label, since models vary in how deep and how controllable that reasoning is.

For a model that streams reasoning, you can tune how hard it thinks with the Thinking Depth selector in the Employee Brain card: Auto, Off, Minimal, Light, Medium, or Deep. Deeper settings use more credits per message because of the additional thinking. For a model that does not stream reasoning, this selector is disabled.

How Models Affect Credits

Credit cost is set per model, not strictly per tier. A cheap Fast-tier model and a cheap Advanced-tier model can land close together, so check the exact rate shown next to each model before switching your whole workspace to it.

What Changes Impact
Cheaper model Fewer credits per message, good for high-volume, everyday work
More capable model More credits per message, reserve for work that truly needs it
Deeper thinking depth Additional credits for the thinking phase, on models that support it

Tips and Tricks

Good to Know

Frequently Asked Questions

Q: Where do I set the AI model for my workspace? A: Go to Settings (gear icon) > Technical > AI Model. In the Employee Brain card, pick the model you want. It saves automatically.

Q: Can different employees use different models? A: Not from the interface today. The model you set on the AI Model page applies to every employee in the workspace.

Q: What is the difference between tiers? A: Fast is built for simple, quick tasks. Standard balances cost and capability for everyday work. Advanced and Frontier handle complex reasoning and the hardest problems, generally at a higher credit cost, though the exact rate depends on the specific model.

Q: Do reasoning models cost more? A: A model that streams a visible thinking process uses more credits when set to a deeper Thinking Depth, because that extra thinking is billed like any other output.

Q: Why can't I change the model? A: Free and Pending plans are locked to the platform default model. Upgrade to Builder plan or above to unlock the full picker.