모델
Claude Sonnet 5.5
Compare
Anthropic logo

Claude Sonnet 5.5

claude-sonnet-5-5llms.txt
Anthropic
Claude Sonnet 5.5 is the next-generation product in Anthropic’s Sonnet model series; Claude Sonnet 5.5 offers the best balance between speed and intelligence. The following five major changes will affect code currently running on Claude Sonnet 5: 1. Using "between_tools" can disable up-front thinking. 2. Forcing the use of tools will result in an error. 3. Thinking content blocks are bound to the model and the conversation. 4. On the Claude API and Google Cloud, the older "computer_20251124" computer tool usage is no longer accepted. 5. The advisor tool will refuse to accept Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisor models. Use between_tools to disable up-front thinking. Forcing tool use will return an error. Thinking blocks are bound to the model and the conversation. On the Claude API and Google Cloud, early computer_20251124 computer tool usage is no longer accepted. The advisor tool no longer accepts Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors.

Pricing

PricingCache ReadWeb SearchCache WriteCache Write 5 MinutesCache Write 1 Hour
$2$10
$0.1/M tokens$0.01/request$2.5/M tokens$2.5/M tokens$4/M tokens

입력 방식

  • Text
  • Vision
  • PDF

출력 방식

  • Text

Context length

  • 1M tokens

Max output

  • 128K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

제공업체

AWS claude-sonnet-5-5
Pricing$2$10
Cache Read$0.1/M tokens
Web Search$0.01/request
Cache Write$2.5/M tokens
Cache Write 5 Minutes$2.5/M tokens
Cache Write 1 Hour$4/M tokens
PrecisionⓘNot Disclosed
Latency3.4S
Throughput96.7TPS
Uptime
99.98% uptime 2 days ago
99.81% uptime yesterday
95.28% uptime today
Anthropic claude-sonnet-5-5
Pricing$2$10
Cache Read$0.1/M tokens
Web Search$0.01/request
Cache Write$2.5/M tokens
Cache Write 5 Minutes$2.5/M tokens
Cache Write 1 Hour$4/M tokens
PrecisionⓘNot Disclosed
Latency5.3S
Throughput95.2TPS
Uptime
99.98% uptime 2 days ago
98.98% uptime yesterday
92.10% uptime today
VertexAI claude-sonnet-5-5
Pricing$2$10
Cache Read$0.1/M tokens
Web Search$0.01/request
Cache Write$2.5/M tokens
Cache Write 5 Minutes$2.5/M tokens
Cache Write 1 Hour$4/M tokens
PrecisionⓘNot Disclosed
Latency2.0S
Throughput107.8TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for claude-sonnet-5-5

Uptime은 지난 72시간 동안 성공한 요청의 비율입니다. AIHubMix는 모든 공급자를 지속적으로 모니터링하며, 오류가 발생하거나 응답이 느린 경우 자동으로 차선의 공급자로 재시도합니다; Latency는 요청의 총 왕복 시간입니다(낮을수록 좋음); Throughput은 모델의 출력 속도입니다(초당 토큰 수, 높을수록 좋음).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-5-5",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is the next-generation product in Anthropic’s Sonnet model series; Claude Sonnet 5.5 offers the best balance between speed and intelligence. The following five major changes will affect code currently running on Claude Sonnet 5: 1. Using "between_tools" can disable up-front thinking. 2. Forcing the use of tools will result in an error. 3. Thinking content blocks are bound to the model and the conversation. 4. On the Claude API and Google Cloud, the older "computer_20251124" computer tool usage is no longer accepted. 5. The advisor tool will refuse to accept Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisor models. Use between_tools to disable up-front thinking. Forcing tool use will return an error. Thinking blocks are bound to the model and the conversation. On the Claude API and Google Cloud, early computer_20251124 computer tool usage is no longer accepted. The advisor tool no longer accepts Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors.

© 2023 - 2026 AIHubMix, LLC

제품

개발자

회사

약관 및 정책