Claude Sonnet 5
Overview
Claude Sonnet 5 is Anthropic’s current Sonnet-tier model, balancing frontier-level reasoning, coding, and agentic capability with strong throughput and cost efficiency. It is Anthropic’s default recommendation. It accepts text and image inputs and offers a 1M-token context window, making it well suited to high-volume production workloads, coding assistants, and long-context agentic tasks.
Key Features
- Balanced Default: Balances capability, throughput, and cost for most production scenarios
- Adaptive Thinking: Supports adaptive reasoning that scales thinking depth on demand
- Long Context: 1M-token context
Best Use Cases
- Production Coding: Coding assistants, code review, and refactoring
- High-Concurrency Services: Online workloads sensitive to throughput and cost
- Long-Context Agents: Tool-calling and multi-step tasks that need long context
Specifications
| Item | Detail |
|---|---|
| Platform model ID | claude-sonnet-5 |
| Context window | 1,000,000 tokens |
| Input modalities | Text, image |
| Reasoning / thinking | Supported (adaptive thinking) |
| First released (market) | 2026-06 |
| Live pricing | See the model marketplace |
Capabilities and Limitations
| Capability | Description |
|---|---|
| Reasoning | Strong. Covers the vast majority of coding and reasoning tasks |
| Multimodal | Supports text and image input |
| Context Window | 1,000,000 tokens |
| Speed | Fast. Balanced default positioning |
Last updated on