Grok 4.6
xai/grok-4.6xAI's frontier model for coding, agentic tasks, and knowledge work, with four reasoning-effort levels.
- Text, Image
- $2 / $6
- 500K
- Aug 12, 2026
Overview
xAI's frontier model for coding, agentic tasks, and knowledge work, with four reasoning-effort levels. It is billed from the same balance as every other model and API here, and the price of each call comes back in the response.
Run Grok 4.6 with an agent
Each guide pairs this model with a currently compatible agent, explains their separate roles, and opens the shared Composer with both selections ready.
- Open guide
Hermes + Grok 4.6
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
OpenClaw + Grok 4.6
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
pi + Grok 4.6
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
DeepSeek Harness + Grok 4.6
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
Kimi Code + Grok 4.6
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
OpenCode + Grok 4.6
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
Pricing
The default plan, in USD per million tokens.
| Meter | Per 1M tokens |
|---|---|
| Input | $2.00 |
| Output | $6.00 |
| Cache read | $0.5 |
| Cache write | $2.50 |
Your balance and per-call records come from /v1/credits and /v1/generation.
Use it
Point your client at the gateway and pass this model id. Nothing else changes.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gateway.agentsky.dev/v1",
apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});
const completion = await client.chat.completions.create({
model: "xai/grok-4.6",
messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response