Claude Sonnet 5
Claude Sonnet 5 is a model developed by Anthropic designed for coding, agentic tasks, and professional workflows. It features a one-million token context window and supports adaptive reasoning with adjustable effort levels.
Claude Sonnet 5 specs and pricing
- Provider: Anthropic
- Released: June 30, 2026
- Context window: 1M tokens
- Max output: 128K tokens
- Input: text, images, files
- Output: text
- Price: $2.00 input / $10 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Claude Sonnet 5 is good at
- Complex software development and debugging
- Analyzing large documents and multi-file projects
- Automated agent tasks requiring multi-step reasoning
To-dos to try with Claude Sonnet 5
- Analyze a large codebase to identify potential security vulnerabilities
- Review a 500-page technical manual to summarize specific compliance requirements
- Use tool calling to execute a multi-step data extraction process from uploaded files
FAQ
- What types of input can Claude Sonnet 5 process? The model accepts text, images, and various file types as input.
- How does the reasoning capability work? Users can select different reasoning effort levels, ranging from low to max, to tailor the model's performance to the complexity of the task.
- How much does Claude Sonnet 5 cost? Claude Sonnet 5 costs $2.00 per million input tokens and $10 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 7 credits ($1 = 100 credits).
- What is the context window of Claude Sonnet 5? Claude Sonnet 5 can read up to 1M tokens at once and write up to 128K tokens in one reply.
- Can I use Claude Sonnet 5 without coding? Yes. In todo.is you pick Claude Sonnet 5 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.