Grok 4.3 pricing for email summarization

Quick start

Call Grok 4.3 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-4.3",
    max_tokens=500,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.005000 per call at standard rates
# Input:  $1.25/MTok
# Output: $2.50/MTok

How Grok 4.3 compares on cost

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

Cheapest viable option: GPT 5.6 Luna at $0.001200/call (76% less, 84/100 quality).

What drives email summarization cost

Individually cheap, collectively expensive. A single thread is small, but summarization runs across an inbox at volume, so per-call price multiplied by message count is the number that matters, not the cost of any one summary. This is the use case where a fast-tier model and batch processing usually beat a smarter model outright.

For Grok 4.3 specifically, that means output tokens cost 2.0x more than input, at $2.50 vs $1.25 per MTok. At this use case’s 3,000/500 token split, output accounts for 25% of the $0.005000 per-call cost.

Grok 4.3 quality benchmarks for email summarization

Benchmark data for email summarization is pending for Grok 4.3. Test against your own evaluation suite before moving to production.

Performance across all task types

Grok 4.3 scores by task type. Email Summarization highlighted.

Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.

About Grok 4.3

xAI publishes no release date for this model; dated to the March 4.20-generation launch whose pricing and 1M context window it shares. Priced from the live models table, which is what matters for costing traffic.

Other models from Grok

You can compare Grok 4.3 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