Grok 4.6 API pricing

Grok 4.6 costs $2 per million input tokens and $6 per million output tokens. A typical chatbot request (about 1,500 input + 400 output tokens) costs $0.0056, or $5.55 per 1,000 requests.

0 characters0 words0 tokens (GPT o200k)

ModelInput tokensPrice / 1M (in → out)Per requestPer month
Grok 4.6$2 → $6

≈ = estimated token count: only OpenAI publishes its tokenizer. Claude counts use Anthropic’s published ratios; use the count_tokens API for an exact number.

Grok 4.6 price per million tokens

USD, xAI standard tier. Prices checked on October 28, 2026.

Token typePrice per 1MWith Batch API
Input$2$1.6
Cached input$0.5$0.4
Output$6$4.8
Input, prompts above 200K$4$3.2
Cached input, above 200K$1$0.8
Output, prompts above 200K$12$9.6

Above 200K prompt tokens the higher rate applies to the whole request.

Model ID: grok-4.6 · Source: docs.x.ai

What a Grok 4.6 request costs

RequestPer requestPer 1,000
Short chat reply
500 input + 200 output tokens
$0.0022$2.25
Chatbot turn with context
1,500 input + 400 output tokens
$0.0056$5.55
Document Q&A (RAG)
8,000 input + 500 output tokens
$0.02$19.80
Long-document summary
150,000 input + 2,000 output tokens
$0.33$327

Token counts are measured with GPT's o200k tokenizer and converted for Grok 4.6 (see below). No caching or batch discount.

Similarly priced models

ModelChatbot requestvs Grok 4.6
Grok 4.7 xAI$0.0056same
Grok 4.5 xAI$0.0056same
Gemini 2.5 Pro Google$0.0060+8%
GPT-4.1 OpenAI$0.0062+12%
o3 OpenAI$0.0062+12%
GPT-6.1 Sol OpenAI$0.0070+26%

Frequently asked questions

How much does the Grok 4.6 API cost?

Grok 4.6 costs $2 per million input tokens and $6 per million output tokens on xAI's standard tier, rising to $4 / $12 for prompts above 200K tokens. Prices checked on October 28, 2026.

How much does one Grok 4.6 request cost?

A typical chatbot request with about 1,500 input and 400 output tokens costs about $0.0056, or $5.55 per 1,000 requests. Paste your own prompt into the calculator on this page for an exact estimate.

Does Grok 4.6 support prompt caching?

Yes. Cached input costs $0.5 per million tokens, 75% less than regular input.

Does Grok 4.6 have a Batch API discount?

Yes: 20% off for requests sent through the Batch API, which may take up to 24 hours. That makes it $1.6 / $4.8 per million input / output tokens.

How are Grok 4.6 tokens counted?

Grok 4.6's tokenizer is not published. We estimate about 1.05× the GPT o200k count for the same text.

More pricing