Anthropic: Claude Sonnet 4.6Active

anthropic/claude-sonnet-4.6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

By:AnthropicInput Type:Output Type:Publish time:2026-02-18

Providers

Route requests across multiple providers. Copy a provider slug to set your preference.

ProviderCache Hit RateContext

Anthropic

anthropic

-$3/ M tokens$15/ M tokensRead:0.3/ M tokensWrite:3.75-6/ M tokens1M1.58s2.56tps

Google Vertex

google-vertex

90.6%$3/ M tokens$15/ M tokensRead:0.3/ M tokensWrite:3.75-6/ M tokens1M1.17s51.2tps

Amazon Bedrock

amazon-bedrock

-$3/ M tokens$15/ M tokensRead:0.3/ M tokensWrite:3.75-6/ M tokens1M--

Uptime

24hours

Direct request success rate on AI Gateway and per-provider.

Oct 26, 19:59

Anthropic100.00%

Google Vertex100.00%

Throughput

24hours

P50 throughput on live AI Gateway traffic, in tokens per second (TPS).

Oct 26, 19:00

Anthropic2.56 tps

Google Vertex51.2 tps

Latency

24hours

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.

Oct 26, 19:00

Anthropic1.58s

Google Vertex1.17s

Activity

Token volume and request traffic to this model over time.

Token Consumption

Oct 25

Anthropic1.3K

Google Vertex148.1M

Amazon Bedrock-

Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis

Gemini 3.1 Pro Preview

Qwen3.7-Max

Claude Sonnet 4.6 Anthropic

Intelligence Index30.1

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token Ranking

Claude CodeClaude Code is Anthropic's agentic coding tool that runs in the terminal, understands a project's codebase, edits files, runs commands, and handles workflows such as tests, debugging and git operations through natural-language instructions. It is also available as IDE extensions (VS Code, JetBrains), a desktop app and a web surface, and is used by developers to build features, fix bugs and automate routine development tasks.

114.6M31.44%

ChatboxChatbox AI is a cross-platform AI chat client and assistant developed by the Chatbox team (chatboxai.app), available on Windows, macOS, Linux, Android, iOS and the web. It lets users connect to many mainstream large language models and OpenAI-compatible API endpoints (including local Ollama models) through a single interface, and supports document/image understanding, knowledge bases, web search, image generation and local storage of chat data.

509.9K

LangChainLangChain is an open-source framework from LangChain (langchain-ai) for building LLM-powered applications and agents, offering a unified interface over models, tools, embeddings, vector stores and agent orchestration. LangChain.js is its TypeScript/JavaScript implementation, with provider packages such as @langchain/openai used to connect applications to chat models. Developers embed it as a library in their own backends, scripts and services rather than using it as a standalone end-user application.

386.0K56.60%

OpenCodeOpenCode is an open-source, MIT-licensed AI coding agent built by the team behind SST (now Anomaly), available as a terminal TUI/CLI, a desktop app, and IDE extensions. It is model-agnostic and works with many LLM providers or local models, letting developers explore codebases, plan changes, edit files, run shell commands, and use LSP and MCP integrations directly from their workflow.

259.3K

HindsightHindsight is an open-source agent memory system built by Vectorize.io that gives AI agents persistent long-term memory through retain, recall, and reflect operations. It organizes knowledge into observations, mental models, and knowledge pages as an alternative to plain RAG or knowledge-graph approaches, and can be self-hosted via Docker/Kubernetes or used as a managed cloud service, with SDKs for Python, TypeScript, Go, a CLI, and an MCP server.

60.1K

OpenQiao Studio ChatOpenQiao Studio Chat is the built-in web chat workspace of the OpenQiao AI model aggregation platform, operated by OpenQiao Singapore. It lets users converse with many different large language models in a browser GUI, with features such as multi-model side-by-side comparison, multimodal file input, Artifacts generation, web search, image generation/editing and voice input/output.

1.1K99.94%

OpenClawOpenClaw is a free, open-source personal AI assistant created by Peter Steinberger and now stewarded by the non-profit OpenClaw Foundation. It runs as a self-hosted Node.js gateway on the user's own machine and connects an LLM-driven agent to everyday messaging channels such as WhatsApp, Telegram, Discord, Slack, Signal and iMessage. Through tools, skills and plugins it can read and write files, run shell commands, control browsers, schedule cron jobs and keep long-term memory for personal and work automation.

Related Models

More models from Anthropic

Anthropic: Claude Haiku 5.5

37.47Btokens

Claude Haiku 5.5 is Anthropic’s cheapest, fastest, and most capable small model to date, built for high-volume, cost-sensitive workloads. It handles summaries, compaction, database queries, classification, and subagent coding tasks with low latency, making it especially effective for live customer support, browser use, and other speed-sensitive applications.

Anthropic: Claude Sonnet 5.5

68.34Btokens

Claude Sonnet 5.5 is Anthropic’s upgraded Sonnet-class model, delivering stronger performance than Claude Sonnet 5 while running over 30% faster and at lower cost for many workloads. It is designed for agentic coding, tool use, and everyday professional tasks, making it well suited for developers and teams building fast, capable AI agents.

Anthropic: Claude Opus 5.5

235.48Btokens

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up. The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.