模型列表
Anthropic Models
Claude series models
Model List
| Model | Description | Context | Features |
|---|---|---|---|
claude-opus-4 | Claude Opus 4 | 200K | Strongest capabilities |
claude-4.5-sonnet | Claude 4.5 Sonnet | 200K | Balanced performance |
claude-sonnet-4 | Claude Sonnet 4 | 200K | High cost-performance ratio |
claude-3.5-sonnet | Claude 3.5 Sonnet | 200K | Stable and reliable |
claude-3-opus | Claude 3 Opus | 200K | Previous generation flagship |
claude-3-haiku | Claude 3 Haiku | 200K | Quick response |
Features
Ultra-long Context
Supports 200K Token context, suitable for long document processing
Strong Coding Ability
Excellent code generation and understanding capabilities
Safe and Reliable
Built-in safety mechanisms for more controllable output
Usage Example
from openai import OpenAI
client = OpenAI(
api_key="sk-your-api-key",
base_url="https://api.smai.ai/v1"
)
response = client.chat.completions.create(
model="claude-4.5-sonnet",
messages=[
{"role": "system", "content": "You are a helpful coding assistant."},
{"role": "user", "content": "Implement quicksort in Python"}
],
max_tokens=2000
)
print(response.choices[0].message.content)Model Selection Recommendations
| Scenario | Recommended Model |
|---|---|
| Complex tasks | claude-opus-4 |
| Daily use | claude-4.5-sonnet |
| Code generation | claude-4.5-sonnet |
| Long documents | claude-opus-4 |
| Quick response | claude-3-haiku |
| Cost-sensitive | claude-sonnet-4 |
Notes
System Prompt
Claude models respond well to system prompts; it is recommended to use system prompts to set the AI's behavior.
max_tokens
It is recommended to explicitly set the max_tokens parameter for Claude models to control output length.