价格

cost = ( input_tokens          × Input
       + 5-minute cache writes × Cache write (5 min)
       + 1-hour cache writes   × Cache write (1 h)
       + cache_read_input_tokens × Cache read
       + output_tokens         × Output ) / 1,000,000

import json
import os
import urllib.request

import anthropic

client = anthropic.Anthropic(base_url="https://api.router.ezat.io", api_key=os.environ["EZAT_API_KEY"])
message = client.messages.create(
    model="anthropic/claude-sonnet-5-5",
    max_tokens=64,
    messages=[{"role": "user", "content": "Say hello in five words."}],
)

# Prices in USD per million tokens, from the public catalog (no key needed).
with urllib.request.urlopen("https://api.router.ezat.io/api/models") as response:
    catalog = json.load(response)["data"]
name = message.model.lower()  # the response echoes the id or alias you sent
pricing = next(m["pricing"] for m in catalog if name == m["id"] or name in m["aliases"])

usage = message.usage
written = usage.cache_creation_input_tokens or 0
written_1h = (usage.cache_creation.ephemeral_1h_input_tokens if usage.cache_creation else 0) or 0
tokens = {
    "input": usage.input_tokens,
    "cacheWrite5m": written - written_1h,
    "cacheWrite1h": written_1h,
    "cacheRead": usage.cache_read_input_tokens or 0,
    "output": usage.output_tokens,
}

# Above a long-context threshold, the whole request uses that tier's prices.
prompt = tokens["input"] + written + tokens["cacheRead"]
prices = {field: pricing[field] for field in tokens}
for tier in sorted(pricing["longContext"], key=lambda tier: tier["minInputTokens"]):
    if prompt >= tier["minInputTokens"]:
        prices.update(tier["prices"])

cost = sum(count * float(prices[field]) for field, count in tokens.items()) / 1_000_000
print(tokens)
print(f"about {cost:.8f} USD")