Grok Build 0.1 pricing for pdf summarization

Quick start

Call Grok Build 0.1 with the OpenAI Python SDK pointed at api.x.ai:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.x.ai/v1",
    api_key=os.environ["XAI_API_KEY"],
)
response = client.chat.completions.create(
    model="grok-build-0.1",
    max_tokens=1500,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0180 per call at standard rates
# Input:  $1.00/MTok
# Output: $2.00/MTok

How Grok Build 0.1 compares on cost

Per-call cost for all models scoring 50+ on pdf summarization benchmarks. Hover for details.

Cheapest viable option: Gemini 3 Flash at $0.0120/call (33% less, 83/100 quality).

What drives pdf summarization cost

PDFs are the worst case for input cost: extracted text carries page furniture, headers, and footnotes that inflate token counts well past what the content warrants. Cleaning the extraction before sending it often cuts more cost than changing models. Long PDFs also routinely cross long-context pricing thresholds, so chunking is both a quality and a cost decision.

For Grok Build 0.1 specifically, that means output tokens cost 2.0x more than input, at $2.00 vs $1.00 per MTok. At this use case’s 15,000/1,500 token split, output accounts for 17% of the $0.0180 per-call cost.

Grok Build 0.1 quality benchmarks for pdf summarization

Performance across all task types

Grok Build 0.1 scores by task type. PDF Summarization highlighted.

Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.

About Grok Build 0.1

xAI's coding-specialised model and the cheapest Grok row on output. Released in early access; xAI publishes release notes at month granularity only.

Other models from Grok

You can compare Grok Build 0.1 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions