xAI
Grok 4.6
xai/grok-4.6
Coming soon
Listed, not sold yet: the provider's resale terms are being confirmed.
Previous xAI frontier model for coding, agentic tasks and knowledge work.
Price
- Input
- $2 per 1M tokens
- Output
- $6 per 1M tokens
- Notes
- Prompts <200K tokens. At or above 200K: $4 in / $12 out. Cached input $0.50.
- Source
- xAI pricing , last verified October 8, 2026
No markup on model usage: you pay the provider's list price.
Model
- Context
- 500K (500,000 tokens)
- Modality
- Text and image
- Input
- text, image
- Output
- text
- Weights
- Closed
- Released
- August 1, 2026
- Tags
- reasoning, coding, agents, vision
Data policy
- Prompts go to
- xAI (SpaceXAI)
- Retention
- API requests and responses stored encrypted for 30 days for abuse auditing, then deleted, never used for training without explicit permission
- Zero data retention
- Available
- Region
- No region guarantee on the default endpoint, US regional endpoint (grok-4.7 and grok-4.6 only) at 1.1x pricing
- Policy
- xAI data policy
Summarised from the provider's published terms. The provider's own policy is what applies.
Call it with any OpenAI SDK
Available when the model is live
from openai import OpenAI
client = OpenAI(
base_url="https://api.safeguard.sh/v1",
api_key="SAFEGUARD_API_KEY",
)
response = client.chat.completions.create(
model="xai/grok-4.6",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Base URL https://api.safeguard.sh/v1, model xai/grok-4.6.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.