Skip to content
ModelCap

Inference provider

xAI: AI models and API pricing

Every tracked model xAI serves through OpenRouter, with xAI's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

xAI serves 7 tracked models through 30 endpoints as of 1 October 2026; the highest-ranked is Grok 4.20 Multi-Agent (ModelCap Index #13); mean measured uptime is 99.90%.

Models served
7
On the ModelCap Index
2
Cheapest output price
$2.00/1M

Language models on xAI (7)

Ranked models first, in ModelCap Index order. Prices are the lowest xAI lists for the model; the endpoint count shows how many deployments carry it.

Language models served by xAI, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Grok 4.20 Multi-AgentxAI#1379.8$1.25$2.502M——4
2Grok 4.7xAI#2972.8$2.00$6.00500K—99.76%5
3Grok Build 0.1xAI—$1.00$2.00256K—100.0%4
4Grok 4.20xAI—$1.25$2.502M—100.0%4
5Grok 4.3xAI—$1.25$2.501M—100.0%4
6Grok 4.5xAI—$2.00$6.00500K—99.87%4
7Grok 4.6xAI—$2.00$6.00500K—99.90%5

xAI on ModelCap: common questions

How many AI models does xAI serve?

7 tracked models as of 1 October 2026: 7 language models (2 with a public ModelCap Index position), across 30 live endpoints observed through OpenRouter.

What is the best model available on xAI?

Grok 4.20 Multi-Agent from xAI is the highest-ranked language model xAI serves, at ModelCap Index position #13 and $2.50 per 1M output tokens on xAI. The table lists every model in Index order.

What is the cheapest model on xAI?

Grok Build 0.1 at $2.00 per 1M output tokens ($1.00 per 1M input), the lowest positive language-token price xAI lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which xAI model has the largest context window?

Grok 4.20 Multi-Agent, served with a 2M-token context window on xAI. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is xAI?

Mean measured uptime across xAI endpoints is 99.90% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the xAI prices come from?

From the OpenRouter catalogue entry for each xAI endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where xAI exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 1 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further