Stream reasoning summaries on grok-4.6

On grok-4.6, set stream: true and read summarized reasoning as it arrives. The xAI SDK exposes chunk.reasoning_content. OpenAI-compatible Responses streams emit response.reasoning_text.delta and response.reasoning_summary_text.delta (print event.delta). Vercel AI SDK surfaces part.type === 'reasoning-delta' with part.text. Those streams are summarizations of internal reasoning. Reasoning tokens bill as part of total consumption (reasoning_tokens in usage).

xAI SDK

import os

from xai_sdk import Client
from xai_sdk.chat import system, user

client = Client(
    api_key=os.getenv("XAI_API_KEY"),
    timeout=3600, # Override default timeout with longer timeout for reasoning models
)

chat = client.chat.create(
    model="grok-4.6",
    messages=[system("You are a highly intelligent AI assistant.")],
)
chat.append(user("A projectile is launched at 30 m/s at 37° above horizontal from a 45 m cliff. Find its speed on impact. (g=10 m/s²)"))

content_started = False

print("\n\n--------- Reasoning ---------", flush=True)

latest_response = None
for response, chunk in chat.stream():
    if chunk.reasoning_content:
        print(chunk.reasoning_content, end="", flush=True)

OpenAI SDK (Responses)

import os
import httpx
from openai import OpenAI

client = OpenAI(
    base_url="https://api.x.ai/v1",
    api_key=os.getenv("XAI_API_KEY"),
    timeout=httpx.Timeout(3600.0),
)

stream = client.responses.create(
    model="grok-4.6",
    input=[
        {"role": "system", "content": "You are a highly intelligent AI assistant."},
        {"role": "user", "content": "A projectile is launched at 30 m/s at 37° above horizontal from a 45 m cliff. Find its speed on impact. (g=10 m/s²)"},
    ],
    stream=True,
)

print("\n\n--------- Reasoning ---------", flush=True)
for event in stream:
    if event.type in ("response.reasoning_text.delta", "response.reasoning_summary_text.delta"):
        print(event.delta, end="", flush=True)

curl

curl https://api.x.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -m 3600 \
  -d '{
    "input": [
        {
            "role": "system",
            "content": "You are a highly intelligent AI assistant."
        },
        {
            "role": "user",
            "content": "A ball is thrown upward at 25 m/s from the top of a 60 m building. Find the maximum height above the ground. (g=10 m/s²)"
        }
    ],
    "model": "grok-4.6",
    "stream": true
}'

Vercel AI SDK

import { xai } from '@ai-sdk/xai';
import { streamText } from 'ai';

const result = streamText({
  model: xai.responses('grok-4.6'),
  system: 'You are a highly intelligent AI assistant.',
  prompt: 'A projectile is launched at 30 m/s at 37° above horizontal from a 45 m cliff. Find its speed on impact. (g=10 m/s²)'
});

console.log("\n\n--------- Reasoning ---------" )

for await (const part of result.fullStream) {
  if (part.type === 'reasoning-delta') {
    process.stdout.write(part.text);
  } 
}

For opaque multi-turn continuity with encrypted thinking traces, see the separate how-to on include: ["reasoning.encrypted_content"] / use_encrypted_content=True.

Pitfalls

• Override client timeouts for reasoning streams. Docs examples use 3600 seconds so the connection does not close early.
• Summarized reasoning streams are documented for grok-4.6 on the Reasoning page. Check that page before assuming other models emit the same fields.
• Reasoning tokens are billed. Watch reasoning_tokens in usage.
• presencePenalty, frequencyPenalty, and stop error on reasoning models. Drop them.
• Console API credits are separate from SuperGrok's weekly pool on grok.com.