All model pricing

xai · GROK

Grok 4.6 API Pricing

Check the model ID and provider reference rates for Grok 4.6, along with current pricing availability on GROK.

How to use Grok 4.6 for coding

Grok 4.6 fits teams testing a log-triage workflow with an OpenAI-compatible chat client. Provide a stack trace and the relevant function, then ask for a ranked list of hypotheses and a check that could rule out each one.

Use OpenAI SDK with an AI in IDE GROK key. View setup guide

Set the OpenAI SDK base URL to the Grok channel endpoint ending in /api/grok/v1 and send grok-4.6 as the model in Chat Completions. Pass the dashboard API key as a Bearer token. Use streaming for interactive text replies in your editor or terminal.

Example API cost at the provider’s standard rate is $0.039 for 15,000 uncached input tokens and 1,500 output tokens. This example assumes no cache usage or paid tools.

Effective GROK API rates

USD per 1M tokens. Quota rates use the current AI in IDE base price × 0.4. Provider prices as of 2026-11-19.

AI in IDE quota rateReference provider rate
Input$0.80$2.00
Cache read$0.20$0.50
Output$2.40$6.00

Use Grok 4.6 in your client

Create a GROK API key in your dashboard, replace YOUR_DASHBOARD_API_KEY, and run this request in a Bash-compatible terminal. The key and its funding source need a positive balance; this request consumes quota.

curl --globoff --fail-with-body 'https://api.aiinide.com/api/grok/v1/chat/completions' \
  -H "Authorization: Bearer YOUR_DASHBOARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"grok-4.6","messages":[{"role":"user","content":"Hello"}],"max_tokens":256}'
View setup guide

Example: usage versus a top-up purchase

Each row uses a 3:1 input-to-output mix and no cache reads. Quota consumed is the cost of that mix. The top-up column is a separate purchase.

Monthly tokensReference API costQuota this example consumesSmallest top-up that covers it
1M$3.00$1.2062.5 dollars of quota, priced at $7.99
10M$30.00$12.0062.5 dollars of quota, priced at $7.99
100M$300.00$120.00125 dollars of quota, priced at $15.99

The quota column is what this token mix consumes. The top-up column is the smallest purchase the slider accepts: $62.5, then steps of $31.25. A small task does not cost that purchase. Examples round top-up quota up to the next $31.25 with a $62.5 minimum. Actual charges vary by usage, plan, context, speed, and promotions.

Protocol, channels, and tools

Protocol
OpenAI Chat Completions
Path
/api/grok/v1/chat/completions
API key header
Authorization: Bearer

Channels and this model ID

  • AWSQ is not compatible with this model ID.
  • CCMAX is not compatible with this model ID.
  • CODEX is not compatible with this model ID.
  • GEMINI is not compatible with this model ID.
  • GROK is compatible with this model ID and uses 0.4× the configured model price when the model is in the catalog.

Tool limits on this channel

The Grok channel accepts text chat only and has no image interface. Streaming and non-streaming responses are both supported.

Grok 4.6 API FAQ

How much does Grok 4.6 API cost?

Reference rates for Grok 4.6 are USD 2 input, USD 0.5 cache read, and USD 6 output per 1M tokens. AI in IDE applies 0.4× its configured model price when charging quota.

What is the Grok 4.6 model ID?

The model ID is grok-4.6.

How do I use Grok 4.6 in my IDE?

Create a GROK API key in your dashboard, replace YOUR_DASHBOARD_API_KEY in the example, and POST an OpenAI-compatible messages body to /chat/completions. The channel is text-only; streaming and non-streaming responses are both supported.