The AI arena is free today

Open Superagent
AnthropicReleased on May 22, 2025

Claude Sonnet 4: Benchmarks, Pricing & Context Window

Claude Sonnet 4 is a language model from Anthropic, released in May 2025, with multimodal input.

Claude Sonnet 4, part of the Claude 4 family, is a significant upgrade to Claude Sonnet 3.7. It excels in coding (72.7% on SWE-bench) and reasoning, responding more precisely to instructions. Sonnet 4 offers an optimal mix of capability

Input
TextImage
Output
Text

Claude Sonnet 4 benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Claude Sonnet 4 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Claude Sonnet 4 holds up as conversations get longer.

Quality Tracker

Claude Sonnet 4 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Mon Oct 19 2026
Notice missing or incorrect data?

Claude Sonnet 4 pricing

Providers

Claude Sonnet 4 starts at $3.00 per million input tokens and $15.00 per million output tokens via Anthropic. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
Anthropic logoAnthropic
$3.00—$15.00200.0K/64.0K
0.40
—
/
Bedrock logoBedrock
$3.00—$15.00200.0K/128.0K
0.50
—
/
Google logoGoogle
$3.00—$15.00200.0K/128.0K
0.40
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Loading chart...
Loading chart...
Loading chart...

Claude Sonnet 4 context window

Input and output token limits for Claude Sonnet 4, plus how it ranks on long-context understanding.

InputOutput
200Ktokens
128Ktokens
≈ 301 pages of text
200K
8K128K1M

Try now

huggle
Claude Sonnet 4in Huggle

Make it with
Claude Sonnet 4.

Claude Sonnet 4

Claude Sonnet 4 latency

Claude Sonnet 4 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Claude Sonnet 4 examples

Recent arena outputs from Claude Sonnet 4, picked from the highest-ranked matchups.

Claude Sonnet 4 license

Claude Sonnet 4 is a proprietary model available under its provider's product and API terms.

License
Proprietary
Hosted access

Proprietary license - usage restrictions apply

Claude Sonnet 4 resources

Official sources for Claude Sonnet 4: provider documentation, official playground, official launch post.

Claude Sonnet 4 vs other models

The most-compared alternatives to Claude Sonnet 4 are Kimi K2 0905, Qwen3 14B, Claude 3.7 Sonnet. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Claude Sonnet 4

Models ranked just above and below Claude Sonnet 4 by LLM Stats score.

 

Kimi K2 0905

Score pending
 

Qwen3 14B

Score pending
 

Claude 3.7 Sonnet

Score pending
 

Qwen3 30B A3B

Score pending
 

Qwen3-235B-A22B-Instruct-2507

Score pending
 

Seed 1.8

Score pending

FAQ

Common questions about Claude Sonnet 4.

When was Claude Sonnet 4 released?

Claude Sonnet 4 was released on May 22, 2025 by Anthropic. This is the official Claude Sonnet 4 release date tracked on LLM Stats.

How much does Claude Sonnet 4 cost?

Claude Sonnet 4 pricing starts at $3.00 per million input tokens and $15.00 per million output tokens via Anthropic, the lowest price among tracked providers.

Who created Claude Sonnet 4?

Claude Sonnet 4 was created by Anthropic.

What is the license for Claude Sonnet 4?

Claude Sonnet 4 is released under the Proprietary license.

Is Claude Sonnet 4 multimodal?

Yes, Claude Sonnet 4 is multimodal and can accept both text and images as input.

What is Claude Sonnet 4 latency?

Claude Sonnet 4 p95 time to first token is 0.40 seconds via Anthropic over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and model workloads.

Where can I use Claude Sonnet 4?

Claude Sonnet 4 is available through 3 providers including Anthropic, Bedrock, Google.

Where is the Claude Sonnet 4 paper or technical report?

Claude Sonnet 4 has a paper or technical report available at https://www.anthropic.com/news/claude-4. Use that source for architecture, training, release and evaluation details.

What models should I compare Claude Sonnet 4 against?

Common Claude Sonnet 4 comparisons include Claude Sonnet 4 vs Kimi K2 0905, Claude Sonnet 4 vs Qwen3 14B, Claude Sonnet 4 vs Claude 3.7 Sonnet. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.