Anthropic Commercial APIStatus: active

Claude 3.5 Sonnet (v2)

Frontier-class workhorse model combining high-speed code generation, computer use, and visual reasoning.

Released: Oct 22, 2024
Last Verified: Aug 10, 2026
Context Window

200k

Tokens

Max Output

8.192k

Output limit

Architecture

Dense Transformer

Model family

Parameters

Not Disclosed

Total / Active

Input Token Cost

$3.00

Per 1M tokens

Output Token Cost

$15.00

Per 1M tokens

Model Overview

Claude 3.5 Sonnet delivers industry-leading performance across coding, visual analysis, and multi-step reasoning with rapid inference speed. Features native support for Computer Use (API-driven UI automation), tool calling, and prompt caching.

Developer Implementation Notes

Supports Computer Use API beta. Prompt caching reduces cached input cost to $0.30 per million tokens.

Key Strengths

  • Industry standard for rapid code generation and refactoring
  • Exceptional visual chart, diagram, and OCR understanding
  • Computer Use API for desktop automation
  • Economical prompt caching ($0.30/MTok)

Limitations & Boundaries

  • 8,192 token output limit compared to 3.7 Sonnet's 128k
  • Lacks native extended chain-of-thought token budgeting

Capabilities & Modalities

Modalities:text, image
Reasoning Chains:No
Tool / Function Calling:Supported
Structured Outputs:Supported
Fine-Tuning:No
Local Deployment:Cloud Only

Best Production Use Cases

  • Everyday software development & IDE integration
  • Document parsing & complex visual extraction
  • Web and desktop UI automated interaction

Verified Benchmark Results

Standardized evaluations with methodology notes and authoritative citation links.

View all industry benchmarks →
Coding Official
SWE-bench Verified

49.0%

Pass@1, standard agentic scaffolding without reasoning tokens

Coding Official
LiveCodeBench

52.4%

Pass@1, 0-shot code generation

Reasoning & Math Official
GPQA Diamond

65.0%

Zero-shot Chain-of-Thought prompting

General Knowledge & Frontier Official
MMLU-Pro

78.0%

5-shot standard Chain-of-Thought prompt

Multimodal Official
MMMU

70.4%

Multimodal college level visual evaluation

Tool & Agentic Official
BFCL (Berkeley Function Calling)

89.2%

AST accuracy across single and multi-turn tool calling

Pricing & Inference Cost Calculator

Token Cost Estimator – Claude 3.5 Sonnet (v2)

Calculate projected inference spend with prompt caching

Quick Workload Presets

Input Tokens / Req2,000
100100k200k
Output Tokens / Req500
5016k32k
Number of Requests1,000
125k50k
Cache Hit Rate0%
0% (No cache)50%90% (Max)
Total Input Spend

$6.0000

2.00M input tokens

Total Output Spend

$7.5000

0.50M output tokens

Estimated Total Cost

$13.50

Avg: $0.01350 / req

Rates: $3.00 in / $15.00 out per million tokens (Anthropic API)Last verified: Aug 10, 2026

Compare with Similar Models

Anthropic

Claude 3.7 Sonnet

Anthropic's first hybrid reasoning frontier model with dynamic thinking budget control and state-of-the-art coding capabilities.

Compare Claude 3.5 Sonnet (v2) vs Claude 3.7 Sonnet
Google DeepMind

Gemini 2.0 Pro (Experimental)

Google's flagship intelligence model engineered for complex coding, mathematical proofs, and 2M token context.

Compare Claude 3.5 Sonnet (v2) vs Gemini 2.0 Pro (Experimental)
OpenAI

OpenAI o3-mini

Next-generation cost-efficient reasoning model optimized for STEM, competitive math, and coding.

Compare Claude 3.5 Sonnet (v2) vs OpenAI o3-mini

Data Accuracy & Verification Notice

AI model specifications, pricing records, and benchmark metrics published on this platform are compiled directly from authoritative sources (official provider documentation, research papers, and verified evaluation harnesses). Benchmark results reflect specific test harnesses and prompting methodologies; scores are not directly comparable across differing evaluation setups.