Home/xAI/Grok 4.6
xAI pricing

Grok 4.6 API Pricing & Cost Calculator

Grok 4.6 is priced at $2 input / $6 output per 1M tokens with a 500K context window and 500K max output, and cached input at $0.50/1M. A 1,000-in / 500-out call costs $0.00500.

Input
$2.00
per 1M tokens
Output
$6.00
per 1M tokens
Context window
500K
tokens
Released
—
Cutoff —
≈ Estimated tokenizer·$2.00 in·$6.00 out (per 1M)
Quick start with a use case
Total cost per call$0.005000
Input$0.002000
Output$0.003000
Cost comparison
Standard
$0.005000
With Caching
$0.004250
Save 15% ↓
With Batch
Not supported
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Detailed pricing

Grok 4.6 pricing breakdown

All pricing dimensions including caching and batch discounts.

TypePrice (per 1M tokens)
Input$2.0000
Output$6.0000
Cached input$0.5000
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Last verified 2026-08-24 · xAI official pricing · ⚠️ Spotted a wrong price? Report in 30s →

How it compares

Grok 4.6 vs alternatives

Single-call cost (1000 input + 500 output tokens) ranked from cheapest.

ModelPer call
Grok 4.6
xAI · this page
$0.005000
DeepSeek V3.2
DeepSeek
$0.000480
GPT-5.6 Luna
OpenAI
$0.000800
Gemini 3.1 Flash Lite
Google
$0.001000
DeepSeek V4-Flash
DeepSeek
$0.001100
GPT-5 mini
OpenAI
$0.001250
Recommended use

When to choose Grok 4.6

Grok 4.6 shines for general-purpose tasks, complex multi-step reasoning, tasks needing real-time information, and image and document understanding. Token counts are estimated within ~10-20% margin.

✓Context window of 500K tokens handles long conversations and large documents.
✓Prompt caching available — significant savings for repeated system prompts.
✓Tool / function calling supported.
FAQ

Frequently asked questions

Grok 4.6 costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. A typical chat call (1000 input + 500 output tokens) costs approximately $0.0050. Use the calculator above to estimate your specific use case.
Grok 4.6 supports a 500K token context window with a max output of 500,000 tokens.
Yes. Cached input is priced at $0.50 per 1M tokens — 75% cheaper than uncached input. This is especially valuable for repeated system prompts, long-context retrieval, and chat threads with shared history.
Yes, Grok 4.6 accepts image input. Vision token pricing is generally calculated based on image dimensions and folded into the input token count. Specific image-specific pricing varies — refer to xAI's official documentation.
Token counts for Grok 4.6 are estimated from character ratios (~10-20% margin). Cost calculations use prices verified on 2026-08-24. For final billing accuracy, always verify with xAI's usage dashboard.
Grok 4.6 does not currently support fine-tuning. Consider another model in the xAI family if fine-tuning is required.
Related

Other models you might consider

DeepSeek
DeepSeek V3.2
DeepSeek's open-weight MoE — top cost/quality ratio
$0.28 in$0.40 out
OpenAI
GPT-5.6 Luna
The cheapest long-context model OpenAI ships — 20x under the flagship
$0.20 in$1.20 out
Google
Gemini 3.1 Flash Lite
Google's cheapest listed model — 250¢/1M input
$0.25 in$1.50 out
DeepSeek
DeepSeek V4-Flash
1M context at budget pricing — $0.44/$1.32
$0.44 in$1.32 out
OpenAI
GPT-5 mini
OpenAI's affordable small model with 272K context
$0.25 in$2.00 out