Claude Sonnet 4 vs Claude Sonnet 5 (Comparative Analysis)
Loading comparison form...
Comparative Analysis: Claude Sonnet 4 vs. Claude Sonnet 5
Want to try out these models side by side?Try Magica for free
Overview
Claude Sonnet 4 was released 1 year before Claude Sonnet 5.
 Claude Sonnet 4 | Claude Sonnet 5 | |
|---|---|---|
Model Provider The organization behind this AI's development | Anthropic | Anthropic |
Input Context Window Maximum input tokens this model can process at once | 1M tokens | 1M tokens |
Output Token Limit Maximum output tokens this model can generate at once | 64K tokens | 128K tokens |
Release Date When this model first became publicly available | May 22, 2025 1 year ago May 22nd, 2025 | June 30, 2026 27 days ago June 30th, 2026 |
Knowledge Cutoff Latest training-data date reported by the provider | January 31, 2025 | Not reported |
Capabilities & Features
Compare supported features, modalities, and advanced capabilities
Claude Sonnet 4 | Claude Sonnet 5 | |
|---|---|---|
Input Types Supported input formats | 🖼️Image📝Text📁File | 📝Text🖼️Image📁File |
Reasoning Controls Defaults and configurable reasoning effort | Optional | Enabled by defaultEffort: Max, Extra High, High, Medium, LowDefault: High |
Output Types Supported output formats | 📝Text | 📝Text |
Tokenizer Text encoding system | Claude | Claude |
Key Features Advanced capabilities | ✓Function CallingStructured Output✓Reasoning Mode✓Content Moderation | ✓Function Calling✓Structured Output✓Reasoning Mode✓Content Moderation |
Pricing
Claude Sonnet 4 is roughly 1.5x more expensive compared to Claude Sonnet 5 for input tokens and roughly 1.5x more expensive for output tokens.
| Claude Sonnet 4 | Claude Sonnet 5 | |
|---|---|---|
Short Context Pricing Base rates before a long-context threshold applies | ||
Input Token Cost Cost per million input tokens | $3.00 per million tokens | $2.00 per million tokens |
Output Token Cost Cost per million output tokens | $15.00 per million tokens | $10.00 per million tokens |
Web Search Cost Additional cost for each web search operation | $0.01 per search | $0.01 per search |
Cache Read Cost Cost to reuse cached input tokens | $0.30 per million tokens | $0.20 per million tokens |
Cache Write Cost Cost to write input tokens to the cache | $3.75 per million tokens | $2.50 per million tokens |
1-Hour Cache Write Cost Cost to cache input tokens for one hour | $6.00 per million tokens | $4.00 per million tokens |
Long Context Pricing Rates for prompts with 200,000 or more tokens | ||
Input Token Cost Long-context input cost per million tokens | $6.00 per million tokens | Not specified |
Output Token Cost Long-context output cost per million tokens | $22.50 per million tokens | Not specified |
Cache Read Cost Long-context cache read cost per million tokens | $0.60 per million tokens | Not specified |
Cache Write Cost Long-context cache write cost per million tokens | $7.50 per million tokens | Not specified |
Benchmarks
Compare relevant benchmarks between Claude Sonnet 4 and Claude Sonnet 5.
| Claude Sonnet 4 | Claude Sonnet 5 | |
|---|---|---|
Intelligence Index Overall model quality across independent evaluations | 28.9 (Artificial Analysis index; higher is better) | 53.4 (Artificial Analysis index; higher is better) |
Coding Index Programming performance across independent evaluations | 37.6 (Artificial Analysis index; higher is better) | 71.5 (Artificial Analysis index; higher is better) |
Agentic Index Ability to complete multi-step agentic tasks | 16.6 (Artificial Analysis index; higher is better) | 46.7 (Artificial Analysis index; higher is better) |
Best Design Arena Score Highest human-preference Elo score across design arenas | 1,198 Elo (#46 in 3D (57.8% win rate)) | 1,345 Elo (#3 in Game Dev (59.9% win rate)) |
At a Glance
Quick overview of what makes Claude Sonnet 4 and Claude Sonnet 5 unique.
Claude Sonnet 4 by Anthropic understands both text and images, can use external tools and APIs, offers advanced reasoning. It can handle standard conversations with its 1M token context window. Premium pricing at $3.00/M input and $15.00/M output tokens. Includes built-in content moderation for safer outputs. Released May 22nd, 2025.Claude Sonnet 5 by Anthropic understands both text and images, can use external tools and APIs, offers advanced reasoning, generates structured data. It can handle standard conversations with its 1M token context window. Reasonably priced at $2.00/M input and $10.00/M output tokens. Includes built-in content moderation for safer outputs. Released June 30th, 2026.Explore More Comparisons
Compare your models with top performers across different categories
Compare Claude Sonnet 4 with:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks
Compare Claude Sonnet 5 with:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks