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-5-5 · Text+Image+PDF

Claude Opus 5.5 Official Specifications, Pricing & Benchmarks

Anthropic frontier coding & autonomous agent flagship with 1M context and 128K output.

📋 Claude Opus 5.5 Official API & System Card Specifications

Verified against official Anthropic developer documentation & pricing

API Model ID: claude-opus-5-5

1. Identity & Capabilities

API Spec
API Model ID
claude-opus-5-5
Release Date
2026-09-22
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
$ 4
Cached Input / 1M
$ 0.2 -95%
Output / 1M Tokens
$ 20
Tiered Pricing Notes
1M context window; Prompt Cache read $0.20/1M (95% off), cache write $5/1M

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1532 AA Index 59
💻 Coding Opus 5 Line
NL2Repo-Bench 75.3 %

Repository-scale code generation from natural language specs

💻 Coding
DeepSWE v1.1 74 %
🤖 Agentic
OSWorld 2.0 70.6 %

OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks.

🤖 Agentic
Terminal Bench 4.0 51.8 %

Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.

🧠 Reasoning
HLE (no tools) 55.6 %

Humanity's Last Exam evaluated without external tools

👁️ Multimodal
BabyVision (w/ Tools) 94.1 %

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Extended Thinking Mode
temperature=1 top_p=1 max_tokens=64,000

💡 When Extended Thinking is enabled, Anthropic API requires temperature=1.0; control depth via budget_tokens.

Standard Non-Thinking Mode
temperature=0.5 top_p=0.95 max_tokens=16,384

📊 Claude Opus 5.5 Full Benchmark Scorecard

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

⚔️ Compare head-to-head

💻 Coding 12 items

BenchCAD (with Python tool) #2/8 96.2%

BenchCAD variant evaluated with access to a Python tool for programmatic CAD reasoning.

SWE-bench Multilingual #2/33 93.9%

A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.

Program Bench #1/18 91.2%

Program Bench evaluates code-generation agents by asking them to recreate a program's behavior from only a compiled binary and documentation.

SWE-Bench Pro #2/52 89.9%

SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.

DeepSWE 1.1 #8/49 74.2%

DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

BenchCAD #2/8 73%

BenchCAD is a benchmark for programmatic CAD reasoning built from 17,900 execution-verified CadQuery programs spanning 106 industrial part families, roughly half anchored to real ISO, DIN, EN, ASME, and IEC specification tables.

Terminal-Bench 4.0 #3/31 66.4%

Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.

FrontierSWE V2 #2/7 62.3%

FrontierSWE V2 evaluates agents on open-ended technical projects and reports mean@5. Kept separate from FrontierSWE V1 dominance-score results, which are not comparable.

SWE-Bench Multimodal #2/7 61.4%

SWE-Bench Multimodal extends SWE-Bench to evaluate language models on software engineering tasks that involve visual inputs such as screenshots, UI mockups, and diagrams alongside code understanding.

Terminal-Bench-Science 0.1 #8/16 58.7%

Terminal-Bench-Science 0.1 is a Stanford-led community benchmark of 70 tasks drawn from scientific research workflows across the life, physical, earth, mathematical, and engineering sciences.

CursorBench 4.0 #2/4 57.8%

CursorBench 4.0 evaluates coding agents on long-horizon coding tasks from real Cursor sessions. Version 4.0 adds longer-horizon tasks; scores are not comparable with CursorBench 3.2.

FrontierCode 1.1 #1/23 54.4%

FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

🤖 Agents & Tools 10 items

OSWorld 2.0 #1/17 81.8%

OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks.

OfficeQA #2/4 78.9%

OfficeQA is a Databricks public benchmark that evaluates end-to-end grounded reasoning over a large corpus of historical U.S. Treasury Bulletin documents. Models must locate relevant tables across the corpus and perform precise numerical reasoning over them.

Toolathlon-Verified #1/5 77.8%

Verified Toolathlon evaluation of agent tool-use capability, as reported in the MiMo-V2.6 release.

LatchBio SpatialBench Verified #2/3 72%

LatchBio SpatialBench Verified tests analysis of spatial transcriptomics data across externally validated problems, requiring the model to answer biological questions about the sample from analysis results.

OfficeQA Pro #4/15 67.7%

OfficeQA Pro evaluates AI models on professional knowledge-work questions and tasks drawn from real office workflows, including document analysis, spreadsheet reasoning, and information synthesis across business domains.

GDPval-AA 2.1 #1/7 1846

Version 2.1 of the Artificial Analysis GDPval evaluation of professional knowledge work, reported as an Elo rating.

LatchBio SingleCellBench #1/3 61.2%

LatchBio SingleCellBench tests analysis of single-cell RNA sequencing data across problems spanning standard workflows such as labeling cell types, finding differentially expressed genes, and correcting batch effects.

AA-Briefcase v1.1 #1/7 1822

AA-Briefcase v1.1 evaluates multi-hour professional office work and reports Elo scores. Kept separate from unversioned AA-Briefcase results.

AutomationBench #14/26 40%

AutomationBench is a tool-use benchmark that evaluates AI agents on automating real-world workflows, testing their ability to orchestrate tools and complete multi-step automation tasks.

Legal Agent Benchmark #4/17 8.3%

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 5.5

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

Compare with these →

Frequently Asked Questions

Is Claude Opus 5.5 open-source or proprietary?

Claude Opus 5.5 (claude-opus-5-5) 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 5.5?

Claude Opus 5.5 supports 1000K input context and 128,000 max output tokens, priced at $4/1M input ($0.2/1M cached) and $20/1M output.