Claude Opus 4.6 advances reasoning and coding, excelling at careful planning and sustaining agentic tasks across large codebases. It introduces a 1M token context window in beta and posts strong long-context retrieval results well above earlier Opus models. The model supports extended thinking for deeper reasoning and can generate up to 128K token outputs, completing larger tasks without splitting them across requests. Opus 4.6 performs strongly across professional domains including financial analysis, legal document review where it reaches 90.2% on BigLaw Bench, research synthesis, code review, and security vulnerability detection. New capabilities include agent teams in Claude Code and improved multi-step planning for spreadsheet work, with better instruction following and consistency. It maintains alignment comparable to its predecessor while showing a low rate of over-refusals among recent Claude models.
Claude Opus 4.6 runs on 3 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Anthropic | US | Enterprise | No | $5.00 | $25.00 |
| AWS Bedrock | EU | Zero data retention | No | $5.00 | $25.00 |
| Google Cloud | US | Enterprise | No | $5.00 | $25.00 |
Training posture across routes: No training on prompts by default.
Each route hosting Claude Opus 4.6 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go β no action required. No training on customer data. EU; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Independent benchmark scores β composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Claude Opus 4.6 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent β Claude Code, Cursor, Codex, and more β and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "anthropic/claude-opus-4-6",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
