One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $2 = $2.00
- Output0.1M x $6 = $0.60
$2.60per session
xAI - Closed weights
Grok 4.6 pricing and specs
Grok 4.6 is a closed-weights model from xAI that costs $2 per 1M input tokens and $6 per 1M output tokens on the first-party API, with a 500K-token context window.
Last verified from docs.x.ai. All sources
- Input / 1M
- $2
- Output / 1M
- $6
- Context
- 500K tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| InputPrompts up to 200,000 tokens | $2 |
| OutputPrompts up to 200,000 tokens | $6 |
| Cache readPrompts up to 200,000 tokens | $0.50 |
| Long-context inputPrompts over 200,000 tokens | $4 |
| Long-context outputPrompts over 200,000 tokens | $12 |
| Long-context cache readPrompts over 200,000 tokens | $1 |
Note: Previous generation, still sold and priced on the official pricing page. max output is not stated because the release notes state 'no text output limit'. Long-context rates apply to all tokens once the prompt reaches 200k. Batch API not supported. Priority Processing 2x; US regional endpoint 1.1x (grok-4.7 and grok-4.6 only). Reasoning effort low/medium/high (default)/xhigh.
Specs
- Context window
- 500,000 tokens
- Release date
- Provider
- xAI
- API model id
grok-4.6- Vercel AI Gateway id
spacexai/grok-4.6- Weights
- Closed weights
What Grok 4.6 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts. These use the base rates, which apply while each request's prompt stays at or under 200,000 tokens; above that, Grok 4.6 bills $4 input and $12 output for the whole request.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $2 = $40.00
- Output5M x $6 = $30.00
$70.00per day
$2,100.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.50 = $0.45
- Uncached input0.1M x $2 = $0.20
- Output0.1M x $6 = $0.60
$1.25per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Grok 4.6 (this page) | $2 | $6 |
| Grok 4.5xAI | $2 | $6 |
| Grok 4.7xAI | $2 | $6 |
| Qwen3.8-2.4T-A95BAlibaba Cloud (Qwen) | $2 | $6 |
| Qwen3.8-MaxAlibaba Cloud (Qwen) | $2 | $6 |
| Grok 4.20xAI | $1.25 | $2.50 |
| Grok 4.20 (Non-Reasoning)xAI | $1.25 | $2.50 |
| Grok 4.20 Multi-Agent BetaxAI | $1.25 | $2.50 |
| Grok 4.3xAI | $1.25 | $2.50 |
Compare
Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.
Related reading
- Grok 4.6: xAI's Agent-Focused Update Matches GPT-5.6 Sol at the Same $2/$6 PriceGrok 4.6 release guide: xAI's agent-focused update matches GPT-5.6 Sol on the AA index at the same $2/$6 pricing, and runs in Cursor and OpenCode.
- GPT-6 Sol vs Claude Opus 5.5 vs Grok 4.7: The September 2026 Price WarGPT-6 Sol vs Claude Opus 5.5 vs Grok 4.7 pricing: verified per-token rates, cost-per-task math and a decision guide for the September 2026 price war.
- Grok Bot's Core Primitive: Every Bot Gets a ComputerGrok Bot gives every Bot a persistent cloud computer with a browser and terminal. Why that one primitive explains routines, Bot teams, and always-on work.
- Grok Bot's Meta Controls: Oversight as a Product PrimitiveGrok Bot's meta controls make agent oversight a product primitive: approval gates, a chief-of-staff structure and escalation learning, not a settings page.
- Grok Bot Has the Right Shape: Four Primitives, Nothing ElseGrok Bot ships four primitives that compose - a text thread, its own cloud computer, a chief of staff over Bots, and show-it-once routines - and nothing else.
- Grok Bot Routines: Automations Without Automation-BuildingGrok Bot routines let you demonstrate a job once, correct it in plain language and hand the Bot the schedule. How it works and how approval gates keep it safe.
FAQ
How much does Grok 4.6 cost per million tokens?
Grok 4.6 costs $2 per 1M input tokens and $6 per 1M output tokens on xAI's first-party API, per docs.x.ai on October 17, 2026. Per 1M tokens, cache reads cost $0.50. Prompts over 200,000 tokens are billed at $4 input and $12 output for the whole request.
What is Grok 4.6's context window?
Grok 4.6 has a 500,000-token context window.
Are Grok 4.6's weights open?
No. Grok 4.6 is a closed-weights model. You call it through xAI's API as grok-4.6 or through Vercel AI Gateway as spacexai/grok-4.6.
When was Grok 4.6 released?
xAI released Grok 4.6 on August 12, 2026.
Sources
Last verified from docs.x.ai.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.