ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Anthropic
Proprietary API Anthropic · claude-sonnet-4-6 · Text+Image+PDF

Claude Sonnet 4.6 Official Specifications, Pricing & Benchmarks

Claude Sonnet 4.6 (claude-sonnet-4-6) by Anthropic, released 2026-02-17, featuring 1,000,000 context window, 128,000 max output tokens, and Text+Image+PDF input.

📋 Claude Sonnet 4.6 Official API & System Card Specifications

Verified against official Anthropic developer documentation & pricing

API Model ID: claude-sonnet-4-6

1. Identity & Capabilities

API Spec
API Model ID
claude-sonnet-4-6
Release Date
2026-02-17
Weight License
Proprietary (Undisclosed)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,000,000 tokens (1000K)
Max Output Tokens
128,000 tokens
Input Modalities
Text + Image + PDF
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 3
Cached Input / 1M
$ 0.3 -90%
Output / 1M Tokens
$ 15

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Reasoning & Tool Config
temperature=0.7 top_p=0.95 max_tokens=65,536

📊 Claude Sonnet 4.6 Full Benchmark Scorecard

22 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

🤖 Agents & Tools 7 items

Tau2 Telecom #4/15 97.9%

τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.

Tau2 Retail #2/8 91.7%

τ²-bench retail domain evaluates conversational AI agents in customer service scenarios within a dual-control environment where both agent and user can interact with tools.

BrowseComp #32/54 74.7%

BrowseComp is a benchmark comprising 1,266 questions that challenge AI agents to persistently navigate the internet in search of hard-to-find, entangled information.

OSWorld #3/5 72.5%

OSWorld: The first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS with 369 computer tasks involving real web and desktop applications, OS file…

Finance Agent #2/8 63.3%

Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.

Finance Agent v2 #8/27 51%

Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.

Legal Agent Benchmark #7/17 5.4%

The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to Claude Sonnet 4.6

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Claude Sonnet 4.6 open-source or proprietary?

Claude Sonnet 4.6 (claude-sonnet-4-6) is a proprietary commercial model by Anthropic. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Claude Sonnet 4.6?

Claude Sonnet 4.6 supports 1000K input context and 128,000 max output tokens, priced at $3/1M input ($0.3/1M cached) and $15/1M output.