Grok 4.20 API Pricing
Grok 4.20 by xAI costs $1.25 per million input tokens and $2.50 per million output tokens.
Price verified from xAI's pricing page.
Rates and limits
- Input / 1M
- $1.25
- Output / 1M
- $2.50
- Cached input / 1M
- $0.20
- Batch discount
- 20% off
- Context window
- 1M tokens
- Released
- November 2025
Pricing note: Priced as grok-4.20-0309 (reasoning and non-reasoning). Prompts of 200K tokens or more are billed at $2.50 in / $0.40 cached / $5 out for the whole request.
What Grok 4.20 costs per month
Token volume split 3:1 between input and output, with no prompt caching.
| Tokens per month | Input / output | Standard | Batch API |
|---|---|---|---|
| 1M | 750K / 250K | $1.56 | $1.25 |
| 10M | 7.5M / 2.5M | $15.63 | $12.50 |
| 100M | 75M / 25M | $156.25 | $125.00 |
Where to run Grok 4.20
Prices above are xAI's direct rates. Cloud platforms can charge differently; the cloud platform view compares them.
- xAI APIDirect API
- OpenRouterCloud / platform
Grok 4.20 pricing FAQ
How much does Grok 4.20 cost per million tokens?
Grok 4.20 costs $1.25 per million input tokens and $2.50 per million output tokens, as listed on xAI's pricing page on September 30, 2026.
How much does Grok 4.20 cost for 10 million tokens a month?
About $15.63 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $12.50 through the batch API.
What is the context window of Grok 4.20?
Grok 4.20 accepts up to 1,000,000 tokens of context.
Does Grok 4.20 support prompt caching?
Yes. Cached input tokens cost $0.20 per million, 84% less than the standard input rate.
Is there a batch discount for Grok 4.20?
Yes. Requests sent through the batch API cost 20% less: $1.00 per million input tokens and $2.00 per million output tokens.
Where can I use the Grok 4.20 API?
Grok 4.20 is available through xAI API and OpenRouter.
Compare with other models
Prices shown as input / output per million tokens. All model prices · Side-by-side comparison