Grok 4.6 pricing

xAI · API id grok-4.6 · verified 2026-11-17

Input$2.00
Cached input (cache hit)$0.50
Cache write—
Output$6.00
Batch discount20%
Context window500,000 tokens
Max output—
Above 200K prompt tokens$4.00 in / $12.00 out

USD per 1M tokens unless noted. Official source

Estimate your workload on Grok 4.6 →

What Grok 4.6 costs for real workloads

WorkloadGrok 4.6Mistral Large 3Mistral Large 4DeepSeek V4 ProGrok 4.7
10,000 chatbot replies
2,000 input + 400 output tokens each, 50% of the prompt cached
$49.00$11.50$16.10$29.48$49.00
One 30-step coding agent run
12K system + tools prompt, 1K output and 3K tool result per step, caching on
$1.45$0.21$0.30$0.38$1.45
1M documents classified (batch)
600 input + 20 output tokens each, batch API where available
$1,056$165$231$871$1,056

Compared with the cheapest other flagship models. Change the numbers in the calculator.

Billing notes

Previous Grok flagship (current: Grok 4.7). Reasoning effort low/medium/high/xhigh (default high). Batch API = 20% off. US regional endpoint (us.api.x.ai) = 1.1x. Requests with >=200K prompt tokens bill ALL tokens at the higher rate. Max output not published.

Where Grok 4.6 ranks by use case

Position by cost among all models that fit each workload (1 = cheapest).

Counting tokens for a prompt? The token counter estimates Grok 4.6 tokens (xAI, DeepSeek, Mistral tokenizer, estimated) and shows the input cost.

Head-to-head comparisons

Other xAI models

All 45 models side by side: LLM API pricing comparison.

FAQ

How much does Grok 4.6 cost per 1M tokens?

Grok 4.6 costs $2.00 per 1M input tokens and $6.00 per 1M output tokens at standard rates (verified 2026-11-17).

Does Grok 4.6 support prompt caching?

Yes. Cached input is billed at $0.50 per 1M tokens.

Is there a batch discount for Grok 4.6?

Yes. The batch API is 20% cheaper than standard requests.

What is the context window of Grok 4.6?

500,000 tokens. Prompts over 200,000 tokens are billed at $4.00 input and $12.00 output for the whole request.