Grok 4.7 API

xai/grok-4.7

xai

xAI's flagship Grok 4.7 — 500K context, vision, always-on reasoning with selectable effort (low to xhigh). Supports Live Search (+$0.30 per call)

Code Examples

from blockrun_llm import LLMClient

client = LLMClient()  # Uses BLOCKRUN_WALLET_KEY (never sent to server)
response = client.chat("xai/grok-4.7", "Hello!")

import { LLMClient } from '@blockrun/llm';

const client = new LLMClient();  // Uses BLOCKRUN_WALLET_KEY (never sent to server)
const response = await client.chat('xai/grok-4.7', 'Hello!');

curl -X POST https://blockrun.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "PAYMENT-SIGNATURE: <payment_header>" \
  -d '{
    "model": "xai/grok-4.7",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 1024
  }'

7.16 s

median latency

85.1 s

p95 latency

99.4%

success rate

100+

calls, last 7 days

On BlockRun since 2026-09-29. Measured on BlockRun over the last 7 days, end to end, successful calls only. Not a vendor benchmark.

Pricing

Input$2.00 / 1M tokens

Output$6.00 / 1M tokens

Context500K tokens

Max Output16K tokens

No markup on official xAI rates; $0.001 fee per call.

Payment

Network

Base

Currency

USDC

Protocol

x402

Pay per request with USDC on Base. No subscription required.

Try It

Send a message to try Grok 4.7

Connect your wallet to enable payments

About xAI Grok 4.7

Grok 4.7 is a reasoning, coding, vision and search-grounded model from xAI with a 500K-token context window and up to 16K tokens of output per call. It is billed per token at the provider's list rate, with no markup on chat tokens. A request whose prompt reaches 200K tokens is billed entirely at the long-context tier, $4.00 in and $12.00 out per million. It is served through BlockRun's OpenAI-compatible API, so it can be called without an account, an API key, or a subscription.

Use Grok 4.7 for

Multi-step reasoning: planning, analysis and math that need thinking before an answer
Coding agents: writing, reviewing and refactoring code across a repository
Reading screenshots, charts, scans and photos alongside text
Answers grounded in live web results
Long documents and whole codebases in a single prompt

What it costs

Grok 4.7 is billed per token. The underlying rates are $2.00 per million input tokens and $6.00 per million output tokens with no platform margin on chat tokens; only a small per-transaction fee covering on-chain settlement is added on top, and the resulting price is quoted in the 402 before you pay. You are charged for the tokens a request actually consumes — there is no monthly commitment and no unused balance to forfeit. With a context window of 500,000 tokens and up to 16,384 tokens of output, a single call can carry a substantial working set.

Specifications

Context window: 500,000 tokens
Maximum output: 16,384 tokens
API compatibility: OpenAI-compatible
Payment: USDC via x402
Categories: reasoning, coding, vision, chat, search

Calling it from your code

Pass xai/grok-4.7 as the model field. Because the endpoint mirrors the OpenAI chat completions schema, any existing OpenAI client works by changing the base URL — streaming, tool use, and multi-turn messages all behave the same way.

The first request returns a 402 carrying the exact price; a signed retry runs it, and client libraries fold the two into one call — how the payment works. See the documentation for request and response shapes, the LLM API page for every model on this endpoint, or browse the full catalog of 90 chat models to compare alternatives.

Grok 4.7 or another model

The closest alternatives by price that do the same kind of work. Each is called on the same endpoint with the same request, so comparing two is a one-line change.

Model	Price	Context
xAI Grok 4.7 (this page)	$2.00 in / $6.00 out per 1M	500K context
Qwen3.8 Max	$2.00 in / $6.00 out per 1M	1M context
xAI Grok 4.5	$2.00 in / $6.00 out per 1M	500K context
xAI Grok 4.6	$2.00 in / $6.00 out per 1M	500K context

Grok 4.7 API questions

How much does the Grok 4.7 API cost?

$2.00 per million input tokens and $6.00 per million output tokens, with cached input at $0.50 per million. There is no markup on chat tokens; a small per-call transaction fee is added, and the price is quoted in the 402 before the call runs.

What is Grok 4.7's context window?

500,000 tokens of context, with up to 16,384 tokens of output per call.

Is the Grok 4.7 API OpenAI-compatible?

Yes. Send an OpenAI chat-completions request with "model": "xai/grok-4.7" to the BlockRun endpoint. An existing OpenAI client works by changing the base URL; streaming and multi-turn messages behave the same way.

Do I need an API key to use Grok 4.7?

No. Each request carries its own payment, so an agent or script can call Grok 4.7 with no account and no key. Teams that prefer one can use an API key with card or invoice billing instead.

Can Grok 4.7 read images?

Yes. Send images in the message content alongside text, in the OpenAI image_url format, and Grok 4.7 reads them with the prompt.

What happens if Grok 4.7 is unavailable?

A request that fails is not charged. If you set "allow_fallback": true, a failed call can be retried on xAI Grok 4.6 instead, never at a higher price than you were quoted.

Related models

Every model on BlockRun is reached through the same endpoint and the same payment flow, so switching is a one-line change to the model field. These are the closest alternatives to Grok 4.7:

xAI Grok 4.5$2.00 in / $6.00 out per 1M
xAI Grok 4.3$1.25 in / $2.50 out per 1M
xAI Grok Build 0.1$1.00 in / $2.00 out per 1M
MiniMax M2.7$0.30 in / $1.20 out per 1M
MiniMax M3$0.30 in / $1.20 out per 1M
xAI Grok 4.6$2.00 in / $6.00 out per 1M

Two ways to run this

Get an API key

Sign in, get a key, and call the same endpoints with usage billed to your account. For teams that want one invoice instead of one wallet.

Get an API key

Or let your agent pay per call, in USDC

No account, no API key. Three steps, and the last one is the request this page is about.

01
Point your agent at BlockRun
Install ClawRouter, or add the BlockRun MCP server to Claude Code, Cursor, Codex or OpenClaw. Any OpenAI-compatible client works too — change the base URL, nothing else.
```
curl -fsSL https://blockrun.ai/ClawRouter-update | bash
```
02
Fund a wallet with USDC
Send USDC to a wallet on Base, Solana or Arc. There is no account to create and no API key to issue: the wallet is the account, and it pays per call.

Call Grok 4.7

The first call returns HTTP 402 with the exact price, your agent signs it, and the answer comes back. Payment settles on-chain; nothing is charged if the call fails.

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

ClawRouter setup →How paying per call works →

Explore everything on BlockRun

AI tools

Models

Integrations

Payment rails

Free to call

Compare