Large Language Models

Claude 3.5 Sonnet

Anthropic's flagship coding, reasoning, and agentic LLM featuring a 200K token context window, Artifacts UI, and Computer Use.

Visitar o site
Claude 3.5 Sonnet
Visualizações -
Visitas mensais --
Classificação global --
Votos 0
X LinkedIn Facebook
Calculadora de Custos de Tokens API

Calculadora de Preços de API e Contexto — Claude 3.5 Sonnet

Calcule o custo por 1.000 chamadas e o total mensal em USD comparando tokens de entrada/saída e janela de contexto.

1 word ≈ 1.33 tokens
Cenários rápidos:
≈ 1,500 words
Tokens
≈ 600 words
Tokens
3,000 calls / mo
/ day

Comparativo de custos de API em tempo real

Claude 3.5 Sonnet Modelo atual Anthropic 200K ctx
Per 1K calls: $18.00 Monthly (30d): $54.00
Claude 3.5 Haiku Anthropic 200K ctx
Per 1K calls: $4.80 Monthly (30d): $14.40
GPT-4o mini OpenAI 128K ctx
Per 1K calls: $0.780 Monthly (30d): $2.34
DeepSeek V2.5 DeepSeek 128K ctx
Per 1K calls: $0.504 Monthly (30d): $1.51
Gemini 1.5 Flash 8B Google 1M ctx
Per 1K calls: $0.195 Monthly (30d): $0.585
Qwen 2.5 72B Alibaba Cloud 128K ctx
Per 1K calls: $1.02 Monthly (30d): $3.06

Tabela de preços por 1M tokens e especificações

Model Input / 1M Output / 1M Cached / 1M Context Window Cost / 1K Calls Monthly USD Best For
Claude 3.5 Sonnet $3.00 $15.00 $0.30 200K $18.00 $54.00 Complex Coding, Agents & Artifacts
Claude 3.5 Haiku $0.80 $4.00 $0.08 200K $4.80 $14.40 Fast Sub-Agents & Real-Time Code
GPT-4o mini $0.15 $0.60 $0.075 128K $0.780 $2.34 High-Throughput Multimodal Apps
DeepSeek V2.5 $0.14 $0.28 $0.014 128K $0.504 $1.51 Ultra-Value Coding & Math API
Gemini 1.5 Flash 8B $0.038 $0.15 $0.01 1M $0.195 $0.585 1M Long-Context & High-Volume
Qwen 2.5 72B $0.35 $0.40 $0.18 128K $1.02 $3.06 Multilingual & Open-Weight Cloud

Sobre esta ferramenta

Claude 3.5 Sonnet by Anthropic is widely adopted by software engineering teams for multi-file code refactoring, autonomous tool-calling agents, visual chart/UI understanding, and structured technical writing across a 200,000-token context window.

Key Capabilities & Engineering Strengths

  • Production-Grade Coding & Agentic Workflows: Excels at SWE-bench repository debugging, pull-request synthesis, interactive Artifacts generation, and GUI-level Computer Use automation.
  • 200K Context + 90% Prompt Caching Savings: Standard API pricing is $3.00 / 1M input tokens and $15.00 / 1M output tokens, with cached prompt reads dropping to $0.30 / 1M tokens and Batch API offering 50% off asynchronous jobs.
  • Interactive Cost Benchmarking: Use the live API Token Cost Calculator above to compare per-1,000-call and 30-day spend against Claude 3.5 Haiku, GPT-4o, DeepSeek V2.5, and Qwen 2.5.
Nome da ferramenta Claude 3.5 Sonnet
Categoria Large Language Models
Modelo de preços Freemium / API ($3 / 1M in)
Tag de tópico LLM, Coding AI, Anthropic, API Pricing
#LLM, Coding AI, Anthropic, API Pricing

Análise de tráfego

Sinais de tráfego, classificação e engajamento desta ferramenta.

Ainda não há dados analíticos

Prévia da interface

Claude 3.5 Sonnet

Perguntas frequentes

How much does the Claude 3.5 Sonnet API cost per million tokens?

Claude 3.5 Sonnet is priced at $3.00 per 1M input tokens and $15.00 per 1M output tokens across a 200K context window. With Anthropic Prompt Caching, repeated input context reads drop by 90% to $0.30 per 1M tokens, and the Message Batches API cuts both input and output rates by 50%.

What is Claude 3.5 Sonnet's maximum context window and output token limit?

Claude 3.5 Sonnet supports a 200,000-token context window (~150,000 English words or ~500 pages of code/docs) and up to 8,192 output tokens per response, making it ideal for multi-file IDE agents like Cursor, Cline, and Claude Code.

Why do developers choose Claude 3.5 Sonnet over GPT-4o for software engineering?

Claude 3.5 Sonnet consistently leads SWE-bench Verified coding evaluations, follows multi-file diff instructions with fewer lazy omissions, renders interactive Artifacts, and supports Computer Use GUI tool execution.

How can I reduce monthly Claude 3.5 Sonnet API bills in production?

Enable Prompt Caching on system prompts and repository context (up to 90% input savings), route simple classification or sub-tasks to Claude 3.5 Haiku ($0.80/$4 per 1M), and use the async Batch API for non-interactive workloads.

Avaliações de usuários

Embed "Featured on ToolAI.io" Badge

Copy the HTML snippet below to display your ToolAI featured badge on your website or docs.

Featured on ToolAI.io