All models
xAI500K context
Grok 4.7
A 500K-token model tuned for quick iteration and direct answers. Useful when latency matters more than ceremony and the prompt is already sharp.
Rate card
Input / 1M0.048
Output / 1M0.145
Cache read / 1M0.012
Official price$2 / $6
1M in + 250K out$0.0846
97.6% below official pricing
Official prices are the vendor's published rates on 3 Nov 2026. Synthetic usage is for illustration. Charges settle against the reported token count.
Use it
The same key and endpoint shape work for every model on RelayTokens. Switch models by changing one field.
Fast drafts
Classification
Search loops
Python
from openai import OpenAI
client = OpenAI(
base_url="https://relaytokens.xyz/v1",
api_key="rt_live_your_key",
)
response = client.chat.completions.create(
model="grok-4.7",
messages=[{"role": "user", "content": "Start with the constraint."}],
)Put Grok 4.7 on the meter.
Prepaid balance. No subscription. No KYC.