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-opus-4-6 · Text+Image+PDF

Claude Opus 4.6 Official Specifications, Pricing & Benchmarks

Classic early-2026 Anthropic flagship scoring 80.8% on SWE-bench Verified and 92.9% on MRCR 1M.

📋 Claude Opus 4.6 Official API & System Card Specifications

Verified against official Anthropic developer documentation & pricing

API Model ID: claude-opus-4-6

1. Identity & Capabilities

API Spec
API Model ID
claude-opus-4-6
Release Date
2026-02-04
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
$ 5
Cached Input / 1M
$ 0.5 -90%
Output / 1M Tokens
$ 25
Tiered Pricing Notes
1M context window (92.9% on MRCR 1M long-context benchmark)

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1508 AA Index 53
💻 Coding
SWE-bench Verified 80.8 %

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

💻 Coding
LiveCodeBench v6 88.8 %

LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code.

🧠 Reasoning
AIME 2026 96.7 %

All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999.

🧠 Reasoning
GPQA Diamond 91.3 %

PhD-level Google-proof science reasoning questions

📚 Knowledge
MMLU-Pro 89.1 %

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.

📚 Knowledge
MRCR 1M 92.9 %

MRCR 1M is a variant of the Multi-Round Coreference Resolution benchmark designed for testing extremely long context capabilities with approximately 1 million tokens. It evaluates models' ability to maintain reasoning and attention across ultra-long conversations.

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Max Effort Thinking Mode
temperature=1 top_p=1 max_tokens=64,000

📊 Claude Opus 4.6 Full Benchmark Scorecard

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

⚔️ Compare head-to-head

🤖 Agents & Tools 8 items

Vending-Bench 2 #4/6 8018

Vending-Bench 2 tests longer horizon planning capabilities by evaluating how well AI models can manage a simulated vending machine business over extended periods.

Tau2 Telecom #1/15 99.3%

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 #1/8 91.9%

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.

DeepSearchQA #3/8 91.3%

DeepSearchQA is a benchmark for evaluating deep search and question-answering capabilities, testing models' ability to perform multi-hop reasoning and information retrieval across complex knowledge domains.

BrowseComp #19/54 84%

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 #2/5 72.7%

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 #3/8 60.7%

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.

Legal Agent Benchmark #8/17 4.2%

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 Opus 4.6

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

Compare with these →

Frequently Asked Questions

Is Claude Opus 4.6 open-source or proprietary?

Claude Opus 4.6 (claude-opus-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 Opus 4.6?

Claude Opus 4.6 supports 1000K input context and 128,000 max output tokens, priced at $5/1M input ($0.5/1M cached) and $25/1M output.