Claude Sonnet 4 2026: Pricing, Benchmarks & Context

Overview

About Claude Sonnet 4

A concise catalog overview. Technical limits and published evaluation evidence are listed separately below.

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.

text

multimodal

reasoning

Published evaluations

Benchmark results

Only results mapped to this exact model and backed by a named source appear here. Different evaluation protocols are not treated as interchangeable.

Source-backed benchmark results for Claude Sonnet 4
Benchmark	Score	Evaluation details	Source
OSWorld-VerifiedA verified computer-use benchmark in which multimodal agents operate desktop applications and are graded from the resulting environment state.	41.4%	Mean task rewardVersion: OSWorld-Verified v1 · Split: Up to 361 tasks, excluding eight Google Drive tasks where required · Harness: Official OSWorld unified environment · Attempts: One run · Tools: GUI interactionProtocol note: Only 100-step general-model rows are included in this normalized snapshot. Individual evaluated-task counts can differ when a task could not run.; Run date: 2025-07-27; Evaluated tasks: 361Methodology	OSWorldBenchmark owner
SWE-Bench VerifiedA human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests.	64.9%	ResolvedVersion: SWE-Bench Verified 500 · Split: Verified, 500 tasks · Harness: mini-SWE-agent / version 1.0.0 · Attempts: One attemptProtocol note: Harness version: 1.0.0; Run date: 2025-07-26Methodology	SWE-benchBenchmark owner

Human preference

Arena results

Arena scores come from blind human preference votes. They are reported separately from task benchmarks and are not used as substitutes for missing benchmark results.

No exact Arena match is available for this model. Similar names and provider variants are not merged automatically.

Technical reference

Specifications and API facts

Technical limits and reference provider prices come from the current catalog unless a reviewed external source is listed. Missing values stay marked as unavailable.

Model

Provider: Anthropic
Release date: Not available in reviewed sources
Catalog added: May 22, 2025
Context window: 1,000,000 tokens
Maximum output: 64,000 tokens
Knowledge cutoff: 2025-01-31
License: Not available in reviewed sources

Capabilities and API

Input types: Image, Text, File
Output types: Text
Reasoning: Supported
Provider endpoint tool parameters: Accepts tool parameters
Base provider API input: $3.00 / 1M tokens
Base provider cached input: $0.30 / 1M tokens
Base provider API output: $15 / 1M tokens
Provider tier at ≥ 200,000 prompt tokens: Input $6.00 / 1M tokensOutput $22.5 / 1M tokensCached input $0.60 / 1M tokens

Provider token rates are context-dependent. The base rates apply below the listed prompt thresholds; the matching tier applies at or above each threshold.

These are reference provider API rates, not Writingmate checkout charges. Access in Writingmate follows the allowances of your Writingmate plan.

Provenance