Grok 4.6 API pricing
xAI charges $2 per million input tokens and $6 per million output tokens for Grok 4.6 (grok-4.6), and $0.5 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.005.
Grok 4.6 price per million tokens
| Token type | Standard |
|---|---|
| Input | $2 |
| Cached input | $0.5 |
| Output | $6 |
API model id: grok-4.6. Grok 4.6 supports a 500K-token context window, up to 500K output tokens, image input, tool calling and reasoning.
What Grok 4.6 costs per request
| Request | 1 request | 1,000 requests | 1M requests |
|---|---|---|---|
| Short chat message (300 in, 200 out) | $0.0018 | $1.80 | $1,800.00 |
| Typical request (1K in, 500 out) | $0.005 | $5.00 | $5,000.00 |
| Long document summary (20K in, 1K out) | $0.046 | $46.00 | $46,000.00 |
| Coding agent step (50K in, 2K out) | $0.11 | $112.00 | $112,000.00 |
At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. xAI counts tokens with its own tokenizer, so the same text can be a different number of tokens.
How Grok 4.6 compares
- For a typical request, Grok 4.6 is cheaper than 42% of the other models on apicost.app.
- GPT-4.1 from OpenAI costs $2 input and $8 output per million tokens, so a typical request is $0.006: 1.2× the price of Grok 4.6.
- Claude Sonnet 5 from Anthropic costs $2 input and $10 output per million tokens, so a typical request is $0.007: 1.4× the price of Grok 4.6.
- Gemini 3.5 Flash from Google Gemini costs $1.5 input and $9 output per million tokens, so a typical request is $0.006: 1.2× the price of Grok 4.6.
Models with a similar price
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Typical request |
|---|---|---|---|---|---|
| Grok 4.5 | xAI | $2 | $0.3 | $6 | $0.005 |
| Grok 4.7 | xAI | $2 | $0.5 | $6 | $0.005 |
| Mistral Medium | Mistral | $1.5 | $0.15 | $7.5 | $0.00525 |
| GPT-4.1 | OpenAI | $2 | $0.5 | $8 | $0.006 |
| o3 | OpenAI | $2 | $0.5 | $8 | $0.006 |
| Gemini 3.5 Flash | Google Gemini | $1.5 | $0.15 | $9 | $0.006 |
| Gemini Omni 1.1 Flash | Google Gemini | $1.5 | – | $9 | $0.006 |
| GPT-5 | OpenAI | $1.25 | $0.125 | $10 | $0.00625 |
Other xAI models
- Grok 4.3 $1.25 / $2.5
- Grok 4.5 $2 / $6
- Grok 4.7 $2 / $6
- Grok 4.20 $1.25 / $2.5
- Grok Build 0.1 $1 / $2
- Grok Code Fast $1 / $2
Every xAI model side by side, with batch, caching and long-context prices: Grok API pricing (xAI). Ways to pay less: batch API, prompt caching, the cheapest models.
Questions and answers
How much does the Grok 4.6 API cost?
xAI charges $2 per million input tokens and $6 per million output tokens for Grok 4.6 (grok-4.6), and $0.5 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.005.
Is there a cheaper way to use Grok 4.6?
Prompt caching lowers the price of input that repeats across requests to $0.5 per million tokens.
What is the context window of Grok 4.6?
Grok 4.6 accepts up to 500,000 input tokens, roughly 375,000 words of English, and writes up to 500,000 output tokens per response. Filling the whole context window once costs $1.00 in input tokens.
Is Grok 4.6 cheaper than GPT-4.1?
Yes. GPT-4.1 from OpenAI costs $2 input and $8 output per million tokens, so a typical request is $0.006: 1.2× the price of Grok 4.6.
Source: xAI pricing, via the LiteLLM price list.