Python: OpenAI SDK trỏ vào các model open-weight

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://llmwithcrypto.com/api/v1",
    api_key=os.environ["LLMWITHCRYPTO_API_KEY"],
)

resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {"role": "system", "content": "Answer in two sentences."},
        {"role": "user", "content": "What is a context window?"},
    ],
    max_tokens=200,
)
print(resp.choices[0].message.content)
print(resp.usage.prompt_tokens, "in,", resp.usage.completion_tokens, "out")

import asyncio
import os

from openai import AsyncOpenAI

client = AsyncOpenAI(
    base_url="https://llmwithcrypto.com/api/v1",
    api_key=os.environ["LLMWITHCRYPTO_API_KEY"],
)
LIMIT = asyncio.Semaphore(4)


async def summarize(text):
    async with LIMIT:
        resp = await client.chat.completions.create(
            model="deepseek-v4.1-flash",
            messages=[
                {"role": "system", "content": "Summarize in one sentence."},
                {"role": "user", "content": text},
            ],
            max_tokens=80,
        )
        return resp.choices[0].message.content


async def main():
    docs = ["First report text...", "Second report text...", "Third report text..."]
    for summary in await asyncio.gather(*(summarize(d) for d in docs)):
        print("-", summary)


asyncio.run(main())

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://llmwithcrypto.com/api/v1",
    api_key=os.environ["LLMWITHCRYPTO_API_KEY"],
)

stream = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Write a haiku about latency."}],
    stream=True,
    stream_options={"include_usage": True},
    max_tokens=120,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    if chunk.usage:
        print("\n", chunk.usage.prompt_tokens, "in,", chunk.usage.completion_tokens, "out")

import os

from openai import OpenAI

# prices per 1M tokens of the models you use, copied from the pricing page
PRICES = {"deepseek-v4-pro": (1.254, 3.762)}

client = OpenAI(
    base_url="https://llmwithcrypto.com/api/v1",
    api_key=os.environ["LLMWITHCRYPTO_API_KEY"],
)
resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Give me three names for a coffee shop."}],
    max_tokens=100,
)
price_in, price_out = PRICES[resp.model]
cost = (resp.usage.prompt_tokens * price_in + resp.usage.completion_tokens * price_out) / 1_000_000
print(resp.choices[0].message.content)
print(f"cost: ${cost:.6f}")