Claude Sonnet 4
Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios. Read more at the [blog post here](https://www.anthropic.com/news/claude-4)
anthropic/claude-sonnet-4
- Context
- 1M tokens
- Completion cap
- 64,000
- Tools
- Yes
- JSON
- No
- Released
- 2025-05-22
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-4",
"messages": [{"role": "user", "content": "Hola"}]
}'Get an API keyFrequently asked questions
- What is Claude Sonnet 4?
- Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios. Read more at the [blog post here](https://www.anthropic.com/news/claude-4) Claude Sonnet 4 runs on the Geek Hub API (OpenAI-compatible). Model id: anthropic/claude-sonnet-4.
- Is Claude Sonnet 4 free?
- No. Input is $3.2702 per 1M tokens and output is $16.3509 per 1M tokens on Geek Hub (markup included).
- What is the context length of Claude Sonnet 4?
- Claude Sonnet 4 has a 1M tokens context window. It supports up to 64,000 completion tokens.
- Does Claude Sonnet 4 support tool calling and structured outputs?
- Claude Sonnet 4 accepts tools and tool_choice for function calling. Structured outputs are not listed for this endpoint.
- When was Claude Sonnet 4 released?
- Claude Sonnet 4 was released on 2025-05-22.
More models from Anthropic
Claude Fable 5Anthropic's most capable model. Adaptive thinking always on. 1M context. Premium for reasoning and agentic workflows.
Claude Haiku 4.5The fastest and cheapest of the Claude family. Extended thinking. Ideal for high volume, classification, extraction.
Claude Opus 4.8 (legacy)Previous Opus generation. Kept for backward compat with existing clients; Opus 5 is 3x cheaper with more context.
Claude Opus 5Opus 5 drops the Opus 4.x pricing to $5/$25 with 1M context and adaptive thinking. The default upgrade in the Opus family.
Claude Sonnet 4.6 (legacy)Sonnet 4.6 kept for backward compat. Sonnet 5 has the same price with 1M context and adaptive thinking.
Claude Sonnet 5Anthropic's sweet spot. Nearly as capable as Opus 5, half the price, same 1M context. Recommended default.