What is Grok 4.6 API?
Grok 4.6 is xAI's large language model for text generation and reasoning tasks, with a 500K token context window and prompt caching support.
Technical Specifications
- Context window: 500,000 tokens
- Supported inputs: Text, File
- Output: Text
Grok 4.6 API Pricing
- Input: $2.6 / 1M tokens (up to 200K context), $5.2 / 1M above 200K
- Output: $7.8 / 1M tokens (up to 200K context), $15.6 / 1M above 200K
- Cached input: $0.65 / 1M (up to 200K), $1.3 / 1M above 200K
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Grok 4.6 is documented as suited to coding, engineering, and office work tasks, including complex multi-step work across codebases and turning ideas into polished applications or work artifacts.
It is also documented for agentic long-running workflows, especially research across unfamiliar domains, analysis, and iterative development of applications and work artifacts.
The model card says it is evaluated on physical-world engineering workflows such as electrical and chip design, procedural 3D modeling via code, and parametric CAD and part generation.
Its documentation also highlights scientific research as a legitimate use case, alongside engineering and creative work.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "x-ai/grok-4-6", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "x-ai/grok-4-6", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"x-ai/grok-4-6","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Tiered pricing: $2.6/$7.8 per 1M tokens up to 200K context, $5.2/$15.6 above 200K. Cached input: $0.65/1M (≤200K) or $1.3/1M (>200K).
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 44.4 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 76.8 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Grok 4.6 This page | Reasoning + agents with long context | |||
| Reasoning + agents with long context | ||||
| Reasoning + agents | ||||
| Chat + assistants |
Grok 4.6 has a 500,000 tokens context window.
Grok 4.6 takes text, file in as input and returns text out.
Use x-ai/grok-4-6 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Grok 4.6 became available on August 7, 2026.
Grok 4.6 is priced at input $2.6 / 1M tokens, output $7.8 / 1M tokens, cached input $0.65 / 1M tokens.
Yes, Grok 4.6 can stream responses as they are generated.
Grok 4.6 was built by xAI .
