xAI (Grok) setup

xAI provides Grok, a cloud-based reasoning model that the coaching platform uses to analyse your coaching transcripts and generate ICF competency assessments. You need an xAI account and an API key. Usage is pay-as-you-go.

Grok's reasoning model is one of the fastest providers for coaching assessment, completing a full PCC evaluation in under 1 minute while maintaining rigorous, honest feedback.

xAI Dashboard

Create API key

View rate limits

Add xAI provider and model

Start ACC AI analysis

AI assessment completed

xAI usage costs

---

Step 1: Create an xAI account

1. Go to console.x.ai
2. Click Sign up
3. Create an account with your email address, or sign in with your X (Twitter) account

Step 2: Add a payment method

1. Once signed in, go to Billing in the left sidebar
2. Click Add payment method and enter your card details

xAI API access requires a payment method. You are only charged for what you use.

Set a spending limit

Under Billing > Limits, you can set a monthly budget to avoid unexpected charges. A limit of $10 per month is more than enough for most coaching use.

Step 3: Create an API key

1. In the xAI console, go to API Keys in the left sidebar
2. Click Create API Key
3. Give it a name (e.g. "Coaching Platform")
4. Copy the key immediately. It will not be shown again.

If you lose the key, you can always create a new one and update it in the coaching platform.

Step 4: Configure the coaching platform

1. Open the coaching platform and go to Settings > AI
2. Select xAI (Grok) as your provider
3. Paste your API key into the API Key field
4. Choose a model. See Choosing a model for recommendations. grok-4-1-fast-reasoning is the recommended model for fast, honest feedback.
5. Click Save

To test the connection, open any session with a recording and transcript, then click Generate AI Assessment.

Speed

Grok's reasoning model is exceptionally fast. A full PCC assessment typically completes in under 1 minute, compared to approximately 4 minutes for Claude Sonnet on the same session. This makes it a good choice if you assess sessions frequently.

Avoid non-reasoning variants

Only the reasoning variants of Grok (like grok-4-1-fast-reasoning) are recommended for coaching assessment. Non-reasoning Grok variants carry the same positivity bias risk as other general-purpose chat models.

For context windows, output token budgets, and rate limits, see API limits.

Troubleshooting

"API key invalid" error

Verify the key is correct. Go to API Keys in the xAI console and check that the key exists and has not been revoked. If in doubt, create a new key and update it in the coaching platform.

"Insufficient credits" error

Your xAI account has run out of credits. Go to Billing in the xAI console and add funds or check your spending limit.

Assessment quality seems inconsistent

Make sure you are using the reasoning model (grok-4-1-fast-reasoning). Non-reasoning Grok variants produce less reliable coaching assessments with potential positivity bias.