GLM 5.3 Flash from Z.ai, with a 1.05M token context window. On Mercato it runs on the cheapest trusted seller, 97% below list right now, and holders pay less again.
Price per 1M tokens
| Price | Input | Output | vs list |
|---|---|---|---|
| Provider list price | $0.00520 | $0.199 | — |
| Market · trusted sellers | $0.000896 | $0.00514 | −97% |
| Ascent holder · −0% today | $0.000896 | $0.00514 | −97% |
| Orbit holder · −0% today | $0.000896 | $0.00514 | −97% |
| Core holder · −0% today | $0.000896 | $0.00514 | −97% |
| Singularity holder · −0% today | $0.000896 | $0.00514 | −97% |
Market depth
90
trusted offers
−85%
cleared vs list, 24h
232,433
requests, 24h
$25.1
paid on the market, 24h
Realized discount, last 48 hours
Request-weighted, across the whole open market, every 2 hours.
Call it
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.mercatocoin.com/v1",
api_key=os.environ["MERCATO_API_KEY"],
)
reply = client.chat.completions.create(
model="z-ai/glm-5.3-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)