Model registry / Anthropic / Claude Sonnet / Claude Sonnet 4.6
Claude Sonnet 4.6
Claude workhorse for coding agents, careful analysis, and production cost control
Line
Claude Sonnet
Weights
API only
Released
2026-02-17
Context
1M
Input
$0.90 / 1M
Output
$5.55 / 1M
Max output
128K
Coverage
not covered yet
Overview
Claude Sonnet 4.6 is Anthropic's workhorse model for coding agents, careful analysis, and production cost control. It is the latest in the claude-sonnet line, succeeding Claude Sonnet 4.5, which was released on 2025-09-29. It has a 1,000,000 token context window and a 128,000 token max output. Pricing starts at $0.90 per million input tokens and $5.55 per million output tokens, with cached input at $0.09 per million tokens. The weights are not open. It supports reasoning mode and tool calling, and accepts image, PDF, and text inputs, returning text.
Specs
Pricing
Against Claude Sonnet 4.5: input $0.43 to $0.90, output $2.14 to $5.55, cached input $0.30 to $0.09.
Range across the hosts that serve it: up to $3.60 per 1M input tokens.
Strengths
- 1,000,000 token context window
- 128,000 token max output
- Supports reasoning and tool calling
- Accepts image, PDF, and text inputs
- Cached input at $0.09 per million tokens
Best for
- Reach for it for coding agents and production workflows
- Reach for it for careful analysis of large documents
- Reach for it for cost-controlled high-volume inference
How to access
31 hosts serve this model at the price above · the maker's documentation
Claude Sonnet: every version
The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.
FAQ
- What is the context window?
- The context window is 1,000,000 tokens.
- Are the weights open?
- No, the weights are not open.
- What input formats does it accept?
- It accepts image, PDF, and text inputs.