grok-4.6

Includes acceptance tests and failed requests, across prices for this model. Private requests are excluded. This sample describes observed traffic; it is not an uptime guarantee.

First text measures dispatch to the first text event. Duration measures dispatch to the recorded finish, including recovery when relevant. Each row excludes missing measurements; percentiles interpolate the sample. 0 settled · 0 released. Outcomes and accounting states are separate counts.

No public requests in this window. Performance remains unknown until traffic is observed.

Endpoint https://aftercore.io/v1/responses

Set AFTERCORE_API_KEY to your Aftercore key. Use a public key for market supply; private keys can only use your own eligible seats. Automatic retries are disabled. Running this example purchases inference at the displayed model’s price.

Grok Build serves this catalogue name as grok-4.6-build. Text Responses only; other protocols and Python/Grok client acceptance remain unverified.

// Each run purchases a new request unless you reuse AFTERCORE_REQUEST_ID. Inspect Usage before retrying.
import { randomUUID } from 'node:crypto';
import OpenAI from 'openai';
const headers = { 'Idempotency-Key': process.env.AFTERCORE_REQUEST_ID || randomUUID(), 'X-Aftercore-Price-Version': "54ac8163-7f8b-4c48-a9bf-72bf8d9b5465", ...(process.env.AFTERCORE_SESSION ? { 'X-Aftercore-Session': process.env.AFTERCORE_SESSION } : {}) };
const client = new OpenAI({ apiKey: process.env.AFTERCORE_API_KEY, baseURL: "https://aftercore.io/v1", maxRetries: 0 });
const stream = await client.responses.create({
  "model": "grok-4.6",
  "stream": true,
  "store": false,
  "max_output_tokens": 32,
  "input": "Say hello in one short sentence."
}, { headers });
for await (const event of stream) {
  if (event.type === 'response.output_text.delta') process.stdout.write(event.delta);
}

Only the supported streaming surface is shown. Output limits on subscription routes are hints; the versioned spending hold is the buyer debit ceiling. Inspect Usage after any interruption before sending another request.