Skip to content

Grok 4.3 API pricing

Grok 4.3 costs $1.25 per million input tokens and $2.50 per million output tokens on xAI's API. Input read back from the prompt cache costs $0.20 per million. A typical support chat reply (1,500 tokens in, 300 out) costs about $0.0026.

Input$1.25 per 1M tokens
Output$2.50 per 1M tokens
Cached input$0.20 per 1M tokens
Long prompts$2.50 in, $5 out per 1M tokens for the whole request once the prompt is over 200,000 tokens
Context window1M tokens
Readstext, images, files
ReleasedApril 30, 2026

What requests cost on Grok 4.3

The same four requests on every page, so you can compare models directly.

RequestTokens in / outPer requestPer 10,000 requests
A support chat reply1,500 / 300$0.0026$26.25
Summarizing a 10-page document6,000 / 500$0.0088$87.50
Sorting a support ticket into a category400 / 5$0.00051$5.13
A question about a 120-page document60,000 / 800$0.077$770

xAI's cheapest model here, Grok Build 0.1, costs 20% less for the same chat reply. Whether it is good enough depends on the request: simple ones (sorting, short summaries, extraction) often are, hard reasoning often isn't.

Other xAI models

ModelInputOutputA chat replyNext to Grok 4.3
Grok Build 0.1$1$2$0.002120% less
Grok 4.7$2$6$0.004883% more
Grok 4.6$2$6$0.004883% more
Grok 4.5$2$6$0.004883% more

Similar price from other companies

ModelInputOutputA chat replyNext to Grok 4.3
GPT-5.4 mini$0.75$4.50$0.00256% less
GPT-6.1 Terra$1$5$0.003014% more
Claude Haiku 4.5$1$5$0.003014% more
GPT-5.1$1.25$10$0.004986% more
GPT-5$1.25$10$0.004986% more

Grok 4.3 pricing questions

How much does the Grok 4.3 API cost per million tokens?

Grok 4.3 costs $1.25 per million input tokens and $2.50 per million output tokens on xAI's API, and input read back from the prompt cache costs $0.20 per million.

How much do 1,000 tokens cost on Grok 4.3?

1,000 input tokens cost $0.00125 and 1,000 output tokens cost $0.0025, at $1.25 and $2.50 per million.

What does one request cost on Grok 4.3?

A typical support chat reply, 1,500 tokens in and 300 out, costs about $0.0026: 1,500 × $1.25 / 1,000,000 plus 300 × $2.50 / 1,000,000.

Is there a cheaper xAI model than Grok 4.3?

Yes. Grok Build 0.1 costs $1 per million input tokens and $2 per million output tokens, so the same chat reply costs about $0.0021. Whether it answers as well depends on the request: test it on your own prompts.

Paying Grok 4.3 prices for every request?

Most apps send simple requests to the same strong model as the hard ones. PromptUnit checks each request your app sends and uses a cheaper model only when it is just as good for that request. You pay 20% of what it saves, and nothing if it saves nothing.

Checked November 6, 2026. Prices are read every day from xAI's pricing page. Context window, inputs and release date come from OpenRouter's public model list.

These are the standard list prices on each provider's own API. Batch, flex and priority tiers, cloud platforms such as Amazon Bedrock or Google Vertex AI, and regional endpoints are priced differently. Request costs above count input and output tokens only, not cache, search or image fees.

Free to reuse (CC BY 4.0): today's list as JSON, and a copy of every day on GitHub.