AI model comparison
GPT-5 vs Claude Sonnet 4
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
OpenAI
GPT-5
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.
- Input / 1M
- $1.25
- Output / 1M
- $10
- Context
- 400K
Anthropic
Claude Sonnet 4
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.
- Input / 1M
- $3
- Output / 1M
- $15
- Context
- 200K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
GPT-5
1.8x cheaper for a typical chat
Higher intelligence score
GPT-5
23 vs 18.9 on Artificial Analysis
Larger context window
GPT-5
400K vs 200K tokens
Newer release
GPT-5
Released August 7, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
GPT-523Claude Sonnet 418.9Coding index
GPT-537.8Claude Sonnet 437.6Agentic index
GPT-5Not availableClaude Sonnet 4Not availablePricing
GPT-5 vs Claude Sonnet 4 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | GPT-5 | Claude Sonnet 4 |
|---|---|---|
| Input tokensPer 1M tokens | $1.25 | $3 |
| Output tokensPer 1M tokens | $10 | $15 |
| Cached input (read)Per 1M tokens | $0.13 | $0.30 |
| Cache writePer 1M tokens | Not available | $3.75 |
| Long-context pricingPer 1M tokens, for very long prompts | Same rate at any length | $6 in / $22.50 out above 200K |
| Web searchPer request | $0.01 | $0.01 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
GPT-5$7.50Claude Sonnet 4$13.50Coding task
30K in, 4K out
GPT-5$77.50$43.75 cachedClaude Sonnet 4$150$69 cachedLong document summary
150K in, 2K out
GPT-5$207.50$38.75 cachedClaude Sonnet 4$480$75 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | GPT-5 | Claude Sonnet 4 |
|---|---|---|
| Context window | 400K tokens | 200K tokens |
| Max output | 128K tokens | 64K tokens |
| Input types | File, Image, Text | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low, Minimal | Not available |
| Default reasoning effort | Medium | Not available |
| Release date | August 7, 2025 | May 22, 2025 |
Features
Supported features
API features available for each model.
| Metric | GPT-5 | Claude Sonnet 4 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Not supported |
| JSON mode | Supported | Not supported |
| Reasoning | Supported | Supported |
| Temperature | Not supported | Supported |
| Stop sequences | Not supported | Supported |
| Deterministic seed | Supported | Not supported |
| Verbosity control | Supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Claude Sonnet 4View full model details- Claude Sonnet 4 vs Claude Sonnet 4.6
- Claude Sonnet 4 vs GPT-5.1
- Claude Sonnet 4 vs GPT-5.1-Codex
- Claude Sonnet 4 vs Claude Opus 4.1
- Claude Sonnet 4 vs o3 Pro
- Claude Sonnet 4 vs Qwen3.5 397B A17B
- Claude Sonnet 4 vs Claude Sonnet 4.5
- Claude Sonnet 4 vs o3
- Claude Sonnet 4 vs Claude Haiku 4.5
- Claude Sonnet 4 vs o4 Mini
- Claude Sonnet 4 vs Gemini 2.5 Pro
- Claude Sonnet 4 vs o1
Our take
GPT-5 is 1.8x cheaper for a typical chat. GPT-5 scores higher on the Artificial Analysis Intelligence Index (23 vs 18.9). GPT-5 has the larger context window (400K vs 200K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is GPT-5 or Claude Sonnet 4 cheaper?
GPT-5 is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-5 costs $1.25 per 1M input tokens and $10 per 1M output tokens, while Claude Sonnet 4 costs $3 per 1M input tokens and $15 per 1M output tokens.
Which has a bigger context window, GPT-5 or Claude Sonnet 4?
GPT-5 supports up to 400K tokens of context, compared with 200K for Claude Sonnet 4.
Is GPT-5 smarter than Claude Sonnet 4?
On the Artificial Analysis Intelligence Index, GPT-5 scores 23 and Claude Sonnet 4 scores 18.9, putting GPT-5 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use GPT-5 and Claude Sonnet 4 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-5 and Claude Sonnet 4 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to GPT-5 and Claude Sonnet 4 at the same time. Compare the answers side by side and keep the best one.