Closed SourceSpaceXAIReleased 2026-08

Grok 4.6

Frontier model for long-running agents, coding, and knowledge work

SpaceXAI has replaced this model with Grok 4.7.

Context window

500K

Input / 1M tokens

$2.00

Output / 1M tokens

$6.00

Provider

SpaceXAI

Per 1M tokens for prompts under 200K tokens: input $2.00, cached input $0.50, output $6.00. Prompts of 200K tokens or more are billed at $4.00 / $1.00 / $12.00 for every token in the request. · Data verified 2026-11-08

Grok 4.6 (August 2026) is SpaceXAI's frontier language model, built on the same 1.5-trillion-parameter V9 foundation as Grok 4.5 with improved supervised fine-tuning and reinforcement learning. It targets long-running agent tasks, complex programming and knowledge work at $2/$6 per 1M tokens. Grok 4.7 (September 2026) replaced it as xAI's flagship at the same price and speed; Grok 4.6 stays in the xAI API, on Amazon Bedrock and in GitHub Copilot, so it mainly suits workloads already tested on it.

Capability index

Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.

Coding
80
Reasoning
80
Math
70
Multimodal
10
Long context
80
Speed
50
Cost efficiency
90

How to access it

xAI API (model ID grok-4.6), Amazon Bedrock, GitHub Copilot, OpenRouter, Vercel and Cloudflare. Grok Build now defaults to Grok 4.7.

Strengths

  • ✓Frontier-level intelligence (61 on Artificial Analysis Index)
  • ✓Exceptional long-running agent capabilities
  • ✓Strong coding and STEM performance
  • ✓Competitive pricing vs frontier models
  • ✓500K context window support

Best for developers who...

Long-running agentic tasksComplex coding and software engineeringKnowledge work and reasoningMulti-step problem solving

When to choose it (and when not to)

Reach for Grok 4.6 when...

  • →Workloads already tested on grok-4.6 (Grok 4.7 costs the same)
  • →When you need frontier-class performance at a lower output price than Claude Opus 5.5 or GPT-6.1 Sol
  • →For tasks requiring sustained reasoning across many steps

Look elsewhere if...

  • ✕New projects: Grok 4.7 has the same price and speed and is xAI's newest model
  • ✕If you need maximum context (older Grok 4.3 offers 1M tokens)
  • ✕If speed is critical (slower than average relative to peers)
  • ✕For requests consistently exceeding 200K tokens (pricing doubles)

How to use it

  • ›Use the 500K context with proper chunking for multi-document analysis
  • ›Use xhigh reasoning effort for complex coding or math tasks
  • ›Monitor 200K token threshold to avoid pricing tier jump

Quickstart

Python
from openai import OpenAI
client = OpenAI(api_key='your-key', base_url='https://api.x.ai/v1')
response = client.chat.completions.create(
  model='grok-4.6',
  messages=[{'role': 'user', 'content': 'Explain quantum computing'}]
)
print(response.choices[0].message.content)

Compatible with OpenAI SDK; configure base_url for xAI API access

API model id: grok-4.6

Benchmarks

BenchmarkScoreNotes
Artificial Analysis Intelligence Index61Matches GPT-5.6 Sol Max; trails Claude Opus 5 and Fable 5 by 1-2 points

Source: Artificial Analysis

Compare Grok 4.6

Compare Grok 4.6 with any other model

Build a comparison →
All model comparisons →

Learn the concepts