Text model

grok-4.7 API pricing

xAI's Grok series — chat plus image generation.

Model IDgrok-4.7

ChatStreamingTool callingVision

Get API Key Run your first request

Call summary

Input

$2.20$1.10/ 1M tokens

Cache write $1.10

Output

$6.60$3.30/ 1M tokens

Cache read $0.275

Context Window

500K

API Endpoints

grok-4.7 API endpoints

One API key — this model is served on the endpoint below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Docs

grok-4.7 pricing tiers

Pricing is tiered by total input length per request (cache included); once a threshold is crossed, the whole request is billed at that tier. All prices are per 1M tokens.

Tier

Standard≤ 200K

Input

$2.20$1.10Cache write: $1.10

Output

$6.60$3.30Cache read: $0.275

Tier

Long context> 200K

Input

$4.40$2.20Cache write: $2.20

Output

$13.20$6.60Cache read: $0.55

Tier	Input	Output
Standard≤ 200K	$2.20$1.10Cache write: $1.10	$6.60$3.30Cache read: $0.275
Long context> 200K	$4.40$2.20Cache write: $2.20	$13.20$6.60Cache read: $0.55

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Not enough production samples yet

This window needs at least 100 eligible requests across 5 independent principals. Metrics appear automatically after that threshold is met.

More Grok models on Router One

6 other Grok models on the same gateway and API key — each page lists endpoints, posted price, and context window.

grok-4.3$0.50 in / $1.00 out per 1M500K context grok-4.5$0.80 in / $2.40 out per 1M500K context grok-4.6$1.10 in / $3.30 out per 1M500K context grok-build-0.1$0.40 in / $0.80 out per 1M500K context grok-imagine-image$0.50 per image grok-imagine-image-quality$0.50 per image

Call grok-4.7 from your code

Your API key works on this endpoint.

Endpoint

/v1/chat/completions

Model ID

grok-4.7

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "grok-4.7",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key

grok-4.7 at a glance

grok-4.7 is a Grok-series text model on Router One. request input ≤ 200,000 tokens: Input $1.10 / 1M tokens, Output $3.30 / 1M tokens, Cache write $1.10 / 1M tokens, Cached input $0.275 / 1M tokens; request input > 200,000 tokens: Input $2.20 / 1M tokens, Output $6.60 / 1M tokens, Cache write $2.20 / 1M tokens, Cached input $0.55 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Context window: 500K tokens. Accepts text, image; returns text. Endpoint: POST /v1/chat/completions (OpenAI-compatible).

grok-4.7 FAQ

How much does grok-4.7 cost on Router One?

request input ≤ 200,000 tokens: Input $1.10 / 1M tokens, Output $3.30 / 1M tokens, Cache write $1.10 / 1M tokens, Cached input $0.275 / 1M tokens; request input > 200,000 tokens: Input $2.20 / 1M tokens, Output $6.60 / 1M tokens, Cache write $2.20 / 1M tokens, Cached input $0.55 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.

Which endpoints serve grok-4.7?

grok-4.7 is served on POST /v1/chat/completions (OpenAI-compatible). Any Router One API key works there.

What is grok-4.7's context window?

grok-4.7 accepts up to 500K tokens of context per request on Router One.

Start using grok-4.7

Create an API key and call grok-4.7 at request input ≤ 200,000 tokens: $1.10 in / $3.30 out per 1M tokens on Router One — pay as you go, with per-request cost and latency visibility.

Get API Key Plans & pay-as-you-go pricing Compare models side by side Quickstart guide