How much does Grok Build 0.1 cost through Final Router?

$1 per million input tokens and $2 per million output tokens - the provider's own list price, with no markup on tokens. A 5.5% fee applies only when you add credits.

Does Grok Build 0.1 train on my data?

No. On the endpoint Final Router calls, xAI does not train on your prompts. Data is processed in US.

How do I call Grok Build 0.1?

Point any OpenAI-compatible client at https://finalrouter.com/api/v1 with your Final Router key and set model to "xai/grok-build-0.1". Your existing code does not change.

xAI · model

Grok Build 0.1

Agentic coding, Cheap, Tool use. Called through Final Router's one OpenAI-compatible endpoint at xAI's list price, with no markup on tokens.

Model id: xai/grok-build-0.1

Input price$1per 1M tokens

Output price$2per 1M tokens

Context window256Ktokens

Typical speed3.6smedian

Quality score88/100composite

ProviderxAIprocessed in US

Cached input$0.25per 1M, cache read

Cache writeIncludedautomatic, no write fee

Note: Prompts over 200k tokens cost $2.00 in and $4.00 out, per 1M.

Verified 2026-08-30xAI's own list price, with no markup on tokens - a 5.5% fee applies only when you add credits.

Call Grok Build 0.1 in one line

Grok Build 0.1 speaks through the same OpenAI-compatible endpoint as every other model. Point your existing client at Final Router, set the model id, and you also get automatic fallback, spend caps and usage tracking - none of which the provider gives you directly.

Call Grok Build 0.1

from openai import OpenAI

client = OpenAI(
    api_key="fr_live_...",                     # your Final Router key
    base_url="https://finalrouter.com/api/v1"  # the only line you change
)

resp = client.chat.completions.create(
    model="xai/grok-build-0.1",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Data & residency

xAI is a United States company and api.x.ai is a single global endpoint with no regional variant to choose. Their published documentation does not name a storage region for API traffic, so this is recorded from where the company and its infrastructure sit rather than from a residency commitment they have made.

Training: not used to train the model. Retention: Requests and responses are kept encrypted for 30 days for auditing and then deleted, and are not used for training; a zero-retention mode exists on their side, set per team on their console rather than per request.

xAI's policy, read 2026-08-30 →

Route it, don't pin it

Name Grok Build 0.1 as your first choice and let a policy fall back to another model when the provider is down - your request still gets answered, and the log shows exactly what happened.

Start free

Grok Build 0.1 FAQ

How much does Grok Build 0.1 cost through Final Router?: $1 per million input tokens and $2 per million output tokens - the provider's own list price, with no markup on tokens. A 5.5% fee applies only when you add credits.
What is Grok Build 0.1's context window?: 256,000 tokens.
Does Grok Build 0.1 train on my data?: No. On the endpoint Final Router calls, xAI does not train on your prompts. Data is processed in US.
How do I call Grok Build 0.1?: Point any OpenAI-compatible client at https://finalrouter.com/api/v1 with your Final Router key and set model to "xai/grok-build-0.1". Your existing code does not change.

Compare with

All comparisons

Grok Build 0.1 vs Muse Spark 1.2 Grok Build 0.1 vs Kimi K2.6 Grok Build 0.1 vs Kimi K2.7 Code Grok Build 0.1 vs Kimi K2.7 Code Highspeed

Muse Spark 1.2Meta

$1.25 in$4.25 out1.048576M ctx

Agentic coding · Huge context · Tool use

Kimi K2.6Moonshot AI

$0.95 in$4 out262K ctx

Cheap · Long context · Tool use

Kimi K2.7 CodeMoonshot AI

$0.95 in$4 out262K ctx

Agentic coding · Long context · Tool use

Kimi K2.7 Code HighspeedMoonshot AI

$1.9 in$8 out262K ctx

Fast · Agentic coding · Tool use

grok-build-0-1Latency and quality are seed figures used for routing order, not billing. Prices are what you are charged.