# xAI — models, pricing & selection | Y-API

> xAI appears on Y-API with two Grok entries, 4.6 and 4.7, both accepting text, image and file input over a 500,000-token window and aimed at coding, agentic work and technical question answering.

This is the markdown representation of https://y-api.bestvirtualgoods.com/models/x-ai. Generated by `scripts/generate-seo-assets.mjs` from the same copy the page renders — do not edit by hand.

Vendor scope: 2 reviewed models.

Sources reviewed: 2026-10-11. Y-API catalog snapshot: 2026-10-11.

## About this vendor

Vendor-level selection advice by Y-API. The per-model pages linked below carry the model-specific checks; nothing here is a measured comparison.

### Where this vendor fits

Grok is the catalog’s second closed-weight frontier family alongside Claude and GPT, and its 500,000-token window sits between the Flash tier and the million-token entries — enough for large repositories, short of the widest windows here.

### What to watch for

Neither entry has a public model card to audit, and the two are priced differently despite sharing a family, so the version number does not tell you which one fits your budget. The 4.7 claim of self-verification is a publisher statement, not a measured property.

## Models on Y-API

Prices are account-credit snapshots from the Y-API catalog. Each model links to its own guide with a cost estimator and a request example.

| Model | Context window | Input / 1M tokens | Output / 1M tokens |
| --- | --- | --- | --- |
| [Grok 4.6](https://y-api.bestvirtualgoods.com/models/x-ai/grok-4.6) | 500,000 | $4.00 | $12.00 |
| [Grok 4.7](https://y-api.bestvirtualgoods.com/models/x-ai/grok-4.7) | 500,000 | $2.00 | $6.00 |

$1 paid adds $10 of credit; the cash equivalent is credit consumed ÷ 10. These are Y-API prices, not the publisher’s list prices.

## Choosing within the lineup

Start with Grok 4.7 as the current flagship and keep 4.6 as a comparison point. Measure the token count of the context you actually need before relying on the 500,000-token window for whole-repository work.

## Before you choose

### Is the 500,000-token window enough for whole-repository work?

It depends on the repository. Measure the token count of the context you actually need before committing, and consider retrieval rather than sending an entire tree in one request.

## Sources & scope

Vendor scope on this site is exactly the reviewed model guides listed above; a vendor page exists only while at least one of its models is reviewed. Claims about architecture or positioning follow the cited pages. We do not publish measured latency, uptime or benchmark scores for any vendor.

- [OpenRouter vendor page](https://openrouter.ai/x-ai)
- [Y-API catalog & prices (JSON)](https://y-api.bestvirtualgoods.com/models.json)

## Links

- HTML version of this page: https://y-api.bestvirtualgoods.com/models/x-ai
- Site index for agents: https://y-api.bestvirtualgoods.com/llms.txt
- Full reference (single file): https://y-api.bestvirtualgoods.com/llms-full.txt
- OpenAPI 3.1 spec: https://y-api.bestvirtualgoods.com/openapi.json
- Model catalog (JSON, no key needed): https://y-api.bestvirtualgoods.com/models.json
- API base URL: `https://api.y-api.bestvirtualgoods.com/v1`
- Contact: support@bestvirtualgoods.com
- Model catalog: https://y-api.bestvirtualgoods.com/models
- Integration guide: https://y-api.bestvirtualgoods.com/docs