Các LLM Khác

Claude (cô-đê)

Model	Latest 1P API model name	Latest AWS Bedrock model name	GCP Vertex AI model name
Claude 3 Opus	`claude-3-opus-20240229`	`anthropic.claude-3-opus-20240229-v1:0`	`claude-3-opus@20240229`
Claude 3 Sonnet	`claude-3-sonnet-20240229`	`anthropic.claude-3-sonnet-20240229-v1:0`	`claude-3-sonnet@20240229`
Claude 3 Haiku	`claude-3-haiku-20240307`	`anthropic.claude-3-haiku-20240307-v1:0`	`claude-3-haiku@20240307`

python (trợ giúp)

import anthropic

client = anthropic.Anthropic(
    # defaults to os.environ.get("ANTHROPIC_API_KEY")
    api_key="sk-xxx",
)
message = client.messages.create(
    model="claude-3-haiku-20240307",
    max_tokens=1000,
    temperature=0,
    system="你是一个助手",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "你是谁？"
                }
            ]
        }
    ]
)
print(message.content)

Tích hợp với LlamaIndex

Cài đặt thư viện

pip install llama-index-llms-anthropic

from llama_index.llms.anthropic import Anthropic
from llama_index.core import Settings
import os
from llama_index.llms.anthropic import Anthropic


os.environ["ANTHROPIC_API_KEY"] = "sk-xxxx"


Settings.tokenizer = Anthropic().tokenizer
# llm = Anthropic(api_key="")
llm = Anthropic(model="claude-3-haiku-20240307")

resp = llm.complete("中国的首都是什么？")
print(resp)

Usage Tier

Usage tier	Requirements to advance to tier	Max usage per month
Credit purchase	Wait after first purchase
Free	N/A	0 days	$10
Build Tier 1	$5	0 days	$100
Build Tier 2	$40	7 days	$500
Build Tier 3	$200	7 days	$1,000
Build Tier 4	$400	14 days	$5,000
Scale	N/A	N/A	N/A

Rate Limits

Cấp 1

Model Tier	Requests per minute (RPM)	Tokens per minute (TPM)	Tokens per day (TPD)
Claude 3 Haiku	50	50,000	5,000,000
Claude 3 Sonnet	50	40,000	1,000,000
Claude 3 Opus	50	20,000	1,000,000

Cấp độ 2

Model Tier	Requests per minute (RPM)	Tokens per minute (TPM)	Tokens per day (TPD)
Claude 3 Haiku	1,000	100,000	25,000,000
Claude 3 Sonnet	1,000	80,000	2,500,000
Claude 3 Opus	1,000	40,000	2,500,000

Mặt tối của mặt trăng

文档

curl https://api.moonshot.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MOONSHOT_API_KEY" \
  -d '{
     "model": "moonshot-v1-8k",
     "messages": [
        {"role": "system", "content": "你是 Kimi，由 Moonshot AI 提供的人工智能助手，你更擅长中文和英文的对话。你会为用户提供安全，有帮助，准确的回答。同时，你会拒绝一切涉及恐怖主义，种族歧视，黄色暴力等问题的回答。Moonshot AI 为专有名词，不可翻译成其他语言。"},
        {"role": "user", "content": "你好，我叫李雷，1+1等于多少？"}
     ],
     "temperature": 0.3
   }'

mô hình / mô hình / mô hình

moonshot-v1-8k
Moonshot-v1-32k
moonshot-v1-128k

价格

LangChain

import os
from langchain_community.chat_models.moonshot import MoonshotChat
from langchain_core.messages import HumanMessage, SystemMessage

# Generate your api key from: https://platform.moonshot.cn/console/api-keys
os.environ["MOONSHOT_API_KEY"] = "sk-xxx"

messages = [
    SystemMessage(
        content="You are a helpful assistant."
    ),
    HumanMessage(
        content="你是谁？"
    ),
]

chat = MoonshotChat()
# or use a specific model
# Available models: https://platform.moonshot.cn/docs
# chat = MoonshotChat(model="moonshot-v1-128k")
r = chat.invoke(messages)
print(r)

ChatGLM

开放平台

定价

curl --location 'https://open.bigmodel.cn/api/paas/v4/chat/completions' \
--header 'Authorization: Bearer <你的apikey>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "glm-4",
    "messages": [
        {
            "role": "user",
            "content": "你好"
        }
    ]
}'

trăm sông / trăm sông / trăm sông

价格

工作台

文档

Tạm thời không có ba trăm ngàn

curl -X POST https://api.baichuan-ai.com/v1/chat/completions\
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer ${API_KEY}"\
     -d '{
          "model": "Baichuan2-Turbo",
          "messages": [
            { "role": "user", "content": "我日薪8块钱，请问在闰年的二月，我月薪多少" }
          ],
          "temperature": 0.3,
          "stream": false
        }'

LangChain中的百川