Grok 4.6

25% OFFx-ai/grok-4.6

Grok 4.6 is xAI's frontier reasoning model for coding, agentic tasks and knowledge work, released in August 2026 as the successor to Grok 4.5. xAI focused it on long-running agents and ambitious interactive and visual projects, such as turning a broad product idea into a working first version and refining it over several rounds. It accepts text and image input with text output and configurable reasoning effort; Grok 4.7 succeeded it in September 2026.

Use in agent Get API key

Input price: $1.50~~$2.00~~USD / 1M tokens
Output price: $4.50~~$6.00~~USD / 1M tokens
Context window: 500K
Max output: 500K

Production route

Try the model

Playground

Open playground

Input⌘ / Ctrl + Enter

Try a prompt

Prompt

Image URL or upload

Upload

500K context500K max outputVision

Input~~$2.00/M~~$1.50/MOutput~~$6.00/M~~$4.50/MCache read~~$0.50/M~~$0.38/M

25% OFF

OutputReady

Your response will appear here

Choose an example or write a prompt, then click Run.

Model card

Specifications

Pricing

Input: $1.50 / 1M tokens
Output: $4.50 / 1M tokens
Cache read: $0.38 / 1M tokens

Context & modalities

Context window: 500,000 tokens
Max output: 500,000 tokens
Input: Text, image
Output: Text

Capabilities

Chat: Supported
Vision: Supported
Reasoning: Supported
Structured output: Supported
Function calling: Supported
Audio input: Not supported

Access

Provider: xAI
Model ID: x-ai/grok-4.6
Execution: sync
Base URL: https://api.sandbase.ai
API: Chat Completions API
Endpoint: /v1/chat/completions

Independent evaluations

Benchmarks

Scores on standardized evaluations, compared with other models on SandBase.

Metrics sourced from Artificial Analysis · Intelligence Index v4.3

Artificial Analysis Intelligence Index: a composite of ten evaluations across reasoning, knowledge, math and coding. Higher is better. Grok 4.6 ranks #15 of 87 models on SandBase.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Chat Completions API endpoint

https://api.sandbase.ai/v1/chat/completions

Model ID

x-ai/grok-4.6

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/chat/completions" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "x-ai/grok-4.6",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"

Choose your model

Compare models

All language models

Model	Context	Input / 1M	Output / 1M	Released
Grok 4.6This model `xAI`	488.3K	$1.50	$4.50	Aug 12, 2026
Grok 4.7 `xAI`	488.3K	$2.00	$6.00	Sep 21, 2026
Grok 4.5 `xAI`	488.3K	$2.00	$6.00	Jul 8, 2026
Grok 4.3 `xAI`	1M	$1.25	$2.50	Apr 30, 2026

Questions

FAQ

How do I call xAI Grok 4.6 through SandBase?

Create a SandBase API key, then send requests with the model ID "x-ai/grok-4.6" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does xAI Grok 4.6 cost?

$1.50 per 1M input tokens and $4.50 per 1M output tokens with the current 25% discount (list price $2 / $6), billed per request from your SandBase balance.

What is the context window of xAI Grok 4.6?

500K tokens of context, with up to 500K output tokens per response.

How does xAI Grok 4.6 score on benchmarks?

xAI Grok 4.6 scores 44.3 on the Artificial Analysis Intelligence Index (v4.3), ranking #15 of 87 models on SandBase; Coding Index 76.8, Agentic Index 53.0. Source: Artificial Analysis, measured as Grok 4.6 (High).

Which features does xAI Grok 4.6 support?

xAI Grok 4.6 supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate xAI account?

No. One SandBase API key and balance gives you access to xAI Grok 4.6 and the other models in the catalog; you do not need to sign up with xAI separately.