Anthropic

Claude Sonnet 4.5

by Anthropictext+image+file->text7 endpoints
Neura Intelligence Index
78.7/ 100
Rank
#38
Confidence
medium
Benchmarks
6(15% coverage)

Overview

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Stop sequences

Modalities

Input
TextImageFile
Output
Text

Technical Specifications

Context Window
1M tokens
Max Output
64K tokens
Knowledge Cutoff
2025-01-31
Tokenizer
Claude
Content Moderation
Enabled
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
September 29, 202511mo

Supported Parameters

include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Benchmark Performance

general

BenchmarkScoreSource
MMMLU
89.1
verified

coding

BenchmarkScoreSource
TerminalBench
50
verified

math

BenchmarkScoreSource
AIME 2025
87
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
83.4
verified

agent

BenchmarkScoreSource
TAU-Bench Retail
86.2
verified
OSWorld
61.4
verified

Performance Over Time

Pricing

Per 1M tokens
Input$3.00
Output$15.00
Cache read$0.30
Cache write$3.75
Added
September 29, 2025
Last synced 9/17/2026