Claude 4.6 Sonnet
Claude 4.6 Sonnet is a text generation model from Anthropic with a 1,000,000-token context window and native tool use.
AnthropicLarge context reasoning with tool and MCP support
Claude 4.6 Sonnet is a large language model developed by Anthropic, released in February 2026. It supports a context window of up to one million tokens and can generate responses of up to 128,000 tokens, making it suited for tasks that involve long documents, extended conversations, or complex multi-step workflows. The model accepts text and image inputs and includes selectable reasoning, tool use, and MCP (Model Context Protocol) server integration as configurable inputs.
Claude 4.6 Sonnet is designed for use cases that benefit from extended context handling, structured reasoning, and agent-style tool orchestration. Its MCP support allows it to connect to external servers and services in a standardized way, enabling more flexible integrations within automated pipelines. Developers building applications that require reading large codebases, processing lengthy documents, or coordinating multi-tool workflows will find these capabilities directly relevant.
What Claude 4.6 Sonnet supports
Large Context Window
Processes up to 1,000,000 tokens in a single context, enabling analysis of long documents, large codebases, or extended conversation histories.
Selectable Reasoning
Supports a configurable reasoning mode that can be toggled as an input, allowing the model to apply extended thinking steps before producing a response.
Tool Use
Accepts structured tool definitions as inputs, enabling the model to call external functions or APIs as part of a response generation workflow.
MCP Server Integration
Supports Model Context Protocol (MCP) server connections as a native input type, allowing standardized integration with external services and data sources.
Vision / Image Input
Accepts image inputs alongside text, supporting tasks such as document analysis, diagram interpretation, and visual question answering.
Long-Form Output
Generates responses of up to 128,000 tokens, suitable for producing detailed reports, long-form code, or extended structured content in a single call.
Ready to build with Claude 4.6 Sonnet?
Get Started FreeBenchmark scores
Scores represent accuracy — the percentage of questions answered correctly on each test.
| Benchmark | What it tests | Standard | Extended Thinking |
|---|---|---|---|
| GPQA Diamond | PhD-level science questions (biology, physics, chemistry) | 79.9% | 87.5% |
| HLE | Questions that challenge frontier models across many domains | 13.2% | 30.0% |
| SciCode | Scientific research coding and numerical methods | 46.9% | 46.8% |
| IFBench | Instruction following accuracy | 41.2% | 56.6% |
| Long Context Reasoning | Reasoning across long documents and contexts | 57.7% | 70.7% |
| TerminalBench Hard | Agentic coding and terminal command tasks | 46.2% | 53.0% |
| τ²-Bench | Agentic tool use in realistic scenarios | 79.5% | 75.7% |
| SWE-bench Verified | Real GitHub issues requiring multi-file code fixes | 79.6% | — |
| OSWorld-Verified | Autonomous computer use and desktop tasks | 72.5% | — |
| Terminal-Bench 2.0 | Agentic coding and terminal command tasks | 59.1% | — |
| ARC-AGI-2 | Novel abstract reasoning and pattern recognition | 58.3% | — |
| MMLU-Pro | Expert knowledge across 14 academic disciplines | 79.1% | — |
| MATH-500 | Undergraduate and competition-level math problems | 97.8% | — |
| MMMB | Multilingual and multimodal understanding | 76.1% | — |
| Finance Agent | Financial analysis and decision-making tasks | 63.3% | — |
| τ²-bench Retail | Agentic tool use in retail scenarios | 91.7% | — |
| τ²-bench Telecom | Agentic tool use in telecom scenarios | 97.9% | — |
| MCP-Atlas Tool Use | Structured tool use via Model Context Protocol | 61.3% | — |
Common questions about Claude 4.6 Sonnet
What is the context window size for Claude 4.6 Sonnet?
Claude 4.6 Sonnet supports a context window of 1,000,000 tokens, meaning it can process up to one million tokens of combined input and conversation history in a single request.
What is the maximum response length?
The model can generate responses of up to 128,000 tokens in a single output, which is suitable for long-form documents, detailed code, or extended structured content.
Does Claude 4.6 Sonnet support image inputs?
Yes, the model supports image inputs alongside text, allowing it to analyze visual content such as diagrams, screenshots, and documents.
What is the pricing for Claude 4.6 Sonnet on MindStudio?
Pricing information for Claude 4.6 Sonnet is not listed in the available metadata. You can check MindStudio's pricing page or the model's detail page for current rates.
What is the knowledge cutoff date for Claude 4.6 Sonnet?
The specific knowledge cutoff date is not included in the available metadata. Anthropic's documentation for Claude Sonnet 4.6 would be the authoritative source for this information.
Does Claude 4.6 Sonnet support tool use and MCP servers?
Yes. The model natively supports tool use and MCP (Model Context Protocol) server connections as configurable inputs, enabling agent-style workflows and integration with external services.
What people think about Claude 4.6 Sonnet
Community discussions mentioning Claude Sonnet 4.6 appear in the context of broader model comparison threads, where users are evaluating coding performance across multiple AI models. Sentiment in coding-focused threads suggests interest in how Sonnet 4.6 performs on real-world software tasks relative to other available models.
Some threads note regressions in general benchmarks for competing models even when agentic coding scores improve, reflecting a common concern about uneven capability trade-offs across model updates. The LocalLLaMA coding comparison thread is the most directly relevant, with users sharing results from testing models on TypeScript projects in practical development scenarios.
Gemini 3.1 livebench results
Livebench just dropped their run of codex 5.3. New SOTA for agentic coding, but regression overall
I compared 8 AI coding models on the same real-world feature in an open-source TypeScript project. Here are the results
Documentation & links
Parameters & options
When enabled, the model will explain its thought process step-by-step before providing a final answer. This can help users understand how the model arrived at its conclusions, but may result in longer responses. The model dynamically decides when and how much to think.
Controls how much the model thinks vs. how quickly it responds. Higher effort produces better quality but uses more tokens and is slower. Recommended: High for coding and agentic work; Medium for general use; Low for short, latency-sensitive tasks. Only applies when Reasoning is enabled.
Explore similar models
AnthropicClaude 5.1 Fable
AnthropicClaude 5.5 Opus
AnthropicClaude 5 Sonnet
Claude 5 Sonnet is Anthropic's flagship text and vision model with a 1,000,000-token context window and extended reasoning.
GoogleGemini 3.8 Flash
OpenAIGPT-5.5
GPT-5.5 is a multimodal text generation model from OpenAI with a 1,000,000-token context window and adjustable reasoning effort.
MetaMuse Spark 1.3
AnthropicClaude 4.5 Haiku
Claude 4.5 Haiku is a text generation model from Anthropic with a 200,000-token context window and image input support.
Start building with Claude 4.6 Sonnet
No API keys required. Create AI-powered workflows with Claude 4.6 Sonnet in minutes — free.