Claude Sonnet 4
VerifiedClaude Sonnet 4 handles complex multimodal tasks with a million-token context.
About Claude Sonnet 4
Claude Sonnet 4 was developed by Anthropic as a closed-weight system. It integrates vision and language processing in a single architecture. The model supports a context window of one million tokens for handling large inputs.
Its design emphasizes coherent analysis across text, images, and attached files. This enables consistent performance on tasks that combine multiple data types. The model remains unavailable for local deployment or weight inspection.
Users apply it to document review, visual question answering, and multi-turn conversations with extensive history. Typical workflows include summarizing long reports that contain embedded images or processing code repositories alongside diagrams.
Capabilities
How Claude Sonnet 4 compares
Claude Sonnet 4 (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Claude Sonnet 4 ranks #111 of 139
Nova Premier 1.0Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long legal and research document review
Processes entire contracts, case files, or research papers up to 1M tokens while preserving nuanced reasoning across the full context.
Multimodal data analysis projects
Combines vision understanding with document analysis to interpret charts, diagrams, and images embedded in large reports or datasets.
Complex software development tasks
Generates and refines code across multiple files while following detailed instructions for architecture and integration requirements.
Strengths & limitations
Strengths
- +Strong reasoning and coherence over long inputs
- +Careful safety alignment
- +High-quality, detailed responses
- +Effective multimodal integration
Limitations
- –Conservative refusals on sensitive topics
- –No native audio or video support
- –May prioritize caution over maximum helpfulness
Cost calculator
Estimate what Claude Sonnet 4 would cost for your usage.
Based on Claude Sonnet 4's $3.00/1M input · $15.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "anthropic/claude-sonnet-4",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: anthropic/claude-sonnet-4
Editor's verdict
Claude Sonnet 4 is Anthropic's proprietary multimodal with a 1000K-token context window.
At $15.00 per 1M output tokens, it is premium-priced for its class.
It is available through Anthropic's API and aggregators like OpenRouter.
Best suited to strong reasoning and coherence over long inputs and careful safety alignment.
Frequently asked questions
The model supports a context length of 1,000,000 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Claude models
Sibling versions in the Claude family from Anthropic.
Similar models
Other multimodal worth comparing.