Getting Started

Prerequisites

Before creating your first Squad Server, you'll need:

  • A syndicAI account — sign up at app.syndicai.dev
  • A payment method — we accept all major credit and debit cards via Stripe

That's it. No Docker, no GPU marketplace accounts, no SSH keys.

Create your first Squad Server

Step 1: Choose your model

After signing in, click Create Squad Server. You'll choose from our supported frontier-class models:

Model Parameters Context Best for
MiniMax M2.5 230B MoE 192K General coding, near-Opus quality
GLM-5 744B MoE 200K Complex reasoning, large codebases
DeepSeek V3.2 671B MoE 128K Frontier-competitive coding
Qwen3-235B 235B MoE 262K Strong coding + reasoning

All models use Mixture-of-Experts (MoE) architecture, meaning only a fraction of parameters are active per token — giving you frontier-class quality with efficient inference.

Step 2: Select your tier

Choose how many GPU-hours per day your squad needs:

  • Starter (2h/day) — Light usage, solo or small squad
  • Standard (4h/day) — Regular daily coding sessions
  • Pro (8h/day) — Full-day coverage for heavy squads

Step 3: Configure squad size

Set the maximum number of squad members (up to 10). Thanks to vLLM's parallel processing, all members can use the server simultaneously with minimal performance degradation.

Step 4: Add credit

Top up your credit balance via Stripe. A minimum balance of $10 is required to create your first Squad Server. Credits are deducted every 15 minutes while your server runs — you only pay for the GPU hours you actually use.

Step 5: Provisioning

syndicAI provisions a dedicated GPU instance for your squad. This typically takes 2–5 minutes. You'll see a real-time progress indicator as your server boots, loads the model weights, and becomes ready.

Get your API endpoint

Once provisioning completes, your Squad Server dashboard shows:

  • API Base URL: https://<your-squad-id>.syndicai.dev/v1
  • API Key: Click "Create API Key" to generate one

Every squad member gets their own API key for individual usage tracking.

Connect your tools

Cursor

  1. Open Cursor Settings → Models → Add Model
  2. Set API Base URL to your Squad Server endpoint
  3. Paste your API Key
  4. Select your model from the dropdown
  5. Start coding

Continue (VS Code extension)

Add to your ~/.continue/config.yaml:

models:
  - name: syndicAI
    provider: openai
    apiBase: https://<your-squad-id>.syndicai.dev/v1
    apiKey: your-api-key
    model: minimax-m2.5

aider

export OPENAI_API_BASE=https://<your-squad-id>.syndicai.dev/v1
export OPENAI_API_KEY=your-api-key
aider --model minimax-m2.5

Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://<your-squad-id>.syndicai.dev/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="minimax-m2.5",
    messages=[{"role": "user", "content": "Write a Python function to merge two sorted lists"}],
)

print(response.choices[0].message.content)

Invite your squad

From your Squad Server dashboard:

  1. Click Invite Members
  2. Share the invite link with your squad
  3. Each member creates their own syndicAI account and joins
  4. Each member generates their own API key

Squad members see shared usage dashboards but manage their own API keys independently.

Next steps