Back to Models
anthropic logo
anthropic/claude-opus-4-6

Claude Opus 4.6

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations. Beyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution. For users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/guides/model-migrations/claude-4-6-opus)

2/4/2026
1,000,000 tokens
#3 Text (spanish)
Input: ¥850/M
Output: ¥4,200/M

Specifications

Modalities

Input
text
image
Output
text

Supported Parameters

include_reasoning
max_tokens
reasoning
response_format
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p
verbosity

Max Output Tokens

128,000

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "anthropic-claude-opus-4-6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Claude Opus 4.6 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

I need to count the number of 'r's in the word 'strawberry'. Let me go through it letter by letter. **s** - not an r **t** - not an r **r** - this is an r ✓ (count: 1) **a** - not an r **w** - not an r **b** - not an r **e** - not an r **r** - this is an r ✓ (count: 2) **r** - this is an r ✓ (count: 3) **y** - not an r There are **3** r's in 'strawberry'.
3.2s response158 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

# Understanding the Error The error `Cannot read properties of undefined (reading 'map')` means that **`users` is `undefined`** when the component renders. You're trying to call `.map()` on a value that doesn't exist yet. This typically happens when: - The parent component doesn't pass the `users` prop - The data is being fetched asynchronously and hasn't loaded yet - The prop name is misspelled ## Solutions ### 1. Add a Default Parameter Value (Simplest Fix) ```javascript function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` ### 2. Add a Guard with Optional Chaining ```javascript function UserList({…
10.5s response599 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

# Code Review: `get_data` Function ## Original Issues Identified 1. **Imports inside function** – reduces clarity and adds per-call overhead 2. **Bare `except`** – catches everything including `KeyboardInterrupt` and `SystemExit` 3. **`== True` comparison** – non-Pythonic 4. **Manual list building** – could use a list comprehension 5. **No logging** – failures happen silently 6. **No response validation** – assumes JSON is always a list of dicts with specific keys 7. **Magic numbers** – `timeout=10`, `sleep(2)` unexplained 8. **Vague function/variable names** – `r`, `data`, `get_data` --- ## Improved Version ```python import logging import time from typing import Any import requests fr…
19.9s response1223 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Claude Opus 4.6 API cost?
On FastMetal, Claude Opus 4.6 is billed per token in yen: ¥850 per 1M input tokens and ¥4,200 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Claude Opus 4.6 with the OpenAI SDK?
Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-opus-4-6" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Claude Opus 4.6?
1,000,000 tokens, shared between the prompt and the response.
How does Claude Opus 4.6 rank?
#16 on the public arena's Japanese board (ELO 1,481). Ranks move as the leaderboard is updated.
What do I need to try Claude Opus 4.6?
Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try Claude Opus 4.6 right now

Claude Opus 4.6 is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Leaderboard

Text
OverallELO: 1,498
#6
JapaneseELO: 1,481
#16
ChineseELO: 1,546
#7
KoreanELO: 1,459
#11
EnglishELO: 1,506
#5
frenchELO: 1,494
#25
germanELO: 1,492
#11
spanishELO: 1,501
#3
russianELO: 1,508
#5
CodingELO: 1,546
#5
MathELO: 1,506
#7
Creative WritingELO: 1,479
#9
Instruction FollowingELO: 1,500
#4
Hard PromptsELO: 1,527
#3
Multi-TurnELO: 1,511
#7
Vision
OverallELO: 1,293
#7
Code
OverallELO: 1,537
#31