Safeguard

xAI

Grok Build 0.1

xai/grok-build-0.1

Coming soon

Listed, not sold yet: the provider's resale terms are being confirmed.

xAI coding model for agentic software engineering, replaces grok-code-fast-1.

Price

Input
$1 per 1M tokens
Output
$2 per 1M tokens
Notes
Prompts <200K tokens. At or above 200K: $2 in / $4 out. Cached input $0.20.
Source
xAI pricing , last verified October 8, 2026

No markup on model usage: you pay the provider's list price.

Model

Context
256K (256,000 tokens)
Modality
Text and image
Input
text, image
Output
text
Weights
Closed
Released
May 1, 2026
Tags
coding, agents

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

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-build-0.1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Base URL https://api.safeguard.sh/v1, model xai/grok-build-0.1.

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.