Skip to content

Model detail

claude-sonnet-4-6

Provided by Anthropic
Pay-as-you-go

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Model specs

Context length
1M
Max output
128K
I/O modalities
Text / Image
Released
2026-02

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • Anthropic Messages /v1/messages POST
  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Input

$3.0000 /1M Tokens

Completion

$15.0000 /1M Tokens

Cache read

$0.3000 /1M Tokens

Cache creation

$3.7500 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Iterative development, codebase navigation, and computer use

Use Sonnet 4.6 for iterative development, complex codebase navigation, end-to-end project management, polished document creation, and confident computer use for web QA and workflow automation.

What should you check before using it?

Test computer use and project management capabilities

Sonnet 4.6 excels at computer use for web QA and workflow automation. Test these specific capabilities to confirm they meet your requirements.

Why use it through MixRoute?

Use the compatible endpoint with stable model ID

Use the confirmed compatible endpoint with model ID claude-sonnet-4-6 through MixRoute.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Share of the same prefix read repeatedly, up to 100%

09

FAQ

Sonnet 4.6 is Anthropic’s most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, and confident computer use.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.