モデル
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

入力モダリティ

  • Text
  • Vision
  • PDF

出力モダリティ

  • 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

プロバイダー

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

Uptime は過去72時間のリクエスト成功率です。AIHubMix は各プロバイダーを常時監視し、エラーや応答遅延が発生した場合は自動的に次善のプロバイダーで再試行します；Latency はリクエストの総往復時間です（低いほど良い）；Throughput はモデルの出力速度です（トークン/秒、高いほど良い）。

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

製品

開発者

会社

規約・ポリシー