Anthropic

Operational· checked every few minutes

Claude Opus 4.6 API

A Claude Opus 4.6 API key at 52% below list, for workloads built on Opus 4.6.

Price per 1M tokens52%off

Input: $2.40~~$5.00~~
Output: $12.00~~$25.00~~
Cached input: $0.24~~$0.50~~

Cache-write pricesAll prices

Get your API key Try it in the playground

Model IDclaude-opus-4-6Updated Oct 16, 2026

chat.py

from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="claude-opus-4-6",
    messages=[
        {"role": "user", "content": "Explain quicksort briefly."},
    ],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK, and the Anthropic SDK and Claude Code. Chat API docs

Context window: 1M tokens
Max output: 128K tokens
Reasoning: low · medium · high · max
Input: Text, Image
Released: Feb 5, 2026
Status: Operational

Pricing

Claude Opus 4.6 API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.

Rate	Zurelay	Anthropic list	You save
Input per 1M tokens	$2.40	~~$5.00~~	52%off
Output per 1M tokens	$12.00	~~$25.00~~	52%off
Cached input per 1M tokens	$0.24	~~$0.50~~	52%off
Cache writes (5 min) per 1M tokens	$3.00	~~$6.25~~	52%off
Cache writes (1 h) per 1M tokens	$4.80	~~$10.00~~	52%off

One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.

Every Claude model and price

Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M

Output tokens per month10M

Zurelay

$240.00

Anthropic list price

$500.00

You save every month$260.00

$3,120 a year

Cost

Claude Opus 4.6 API cost, worked out. And compared.

Typical workloads at Zurelay's live prices next to the list price, and what other places charge for the same model.

Chatbot
50,000 requests a month, 1,500 tokens in and 300 out, 30% of the input cached. $0.00623 a request.
$311.40a month~~$648.75~~ at list
Documents
20,000 requests a month, 8,000 tokens in and 500 out, 20% of the input cached. $0.0217 a request.
$434.88a month~~$906.00~~ at list
Coding agent
5,000 requests a month, 40,000 tokens in and 1,500 out, 85% of the input cached. $0.0406 a request.
$202.80a month~~$422.50~~ at list
Classification
1,000,000 requests a month, 400 tokens in and 5 out. $0.00102 a request.
$1,020a month~~$2,125~~ at list

Where to buy Claude Opus 4.6

Prices per 1M tokens

Seller	Input	Output	vs Anthropic
Anthropic List price, direct	$5.00	$25.00	—
OpenRouter List price, plus 5.5% on card top-ups	$5.00	$25.00	+5.5%
Zurelay No fee to add credit	$2.40	$12.00	52%off

OpenRouter's fee as its pricing page listed it on October 28, 2026. Zurelay's prices are live. Some labs also discount batch or off-peak requests.

Overview

What is Claude Opus 4.6?

Claude Opus 4.6 is the February 2026 Opus model that brought adaptive thinking and the max effort level to the Opus line. The Zurelay Claude Opus 4.6 API serves the same model through OpenAI-compatible and Anthropic-compatible endpoints at 52% below Anthropic's list price. It is the newest Opus that still accepts temperature and budget_tokens, and it uses the tokenizer from before Opus 4.7.

Claude Opus 4.6 was released by Anthropic on February 5, 2026. At launch Anthropic highlighted more careful planning, longer agentic runs, more reliable work in large codebases, and stronger code review and debugging than Opus 4.5. On Zurelay, the Claude Opus 4.6 API uses the model ID claude-opus-4-6 and costs $2.40 per 1M input tokens and $12.00 per 1M output tokens, compared with Anthropic's list price of $5.00 and $25.00.

Opus 4.6 introduced adaptive thinking to the Opus line, where the model decides when deeper reasoning helps, along with a max effort level above high. Effort runs low, medium, high and max, with high as the default; xhigh only arrived with Opus 4.7. Thinking stays off unless you enable it. The older budget_tokens mode is deprecated on this model but still works, which makes Opus 4.6 a bridge for code that has not moved to adaptive thinking yet.

The specs: a 1M-token context window, up to 128K output tokens, text and image input, and text output. The 1M window launched as a beta and now runs at Anthropic's standard pricing. Images top out at 1,568 pixels on the long edge. Knowledge is most reliable through May 2025, with training data through August 2025. The minimum cacheable prompt is 4,096 tokens, higher than on later Opus models, so short prompts will not cache.

Why still run Opus 4.6? It is the newest Opus that accepts temperature, top_p and top_k; Anthropic refuses all three from Opus 4.7 on, and Zurelay leaves them out of those requests. It uses the older tokenizer, while Opus 4.7 and later can use up to about 35% more tokens for the same text. On the Messages API it returns summarized thinking text by default, where later models return it empty unless you opt in. Anthropic's current retirement date for it is not sooner than February 5, 2027.

Strengths

Where Claude Opus 4.6 shines. And what teams build with it.

Sampling parameters still work

The newest Opus that accepts temperature, top_p and top_k, for pipelines that tune output variety with parameters instead of prompts.

Fewer tokens for the same text

It predates the Opus 4.7 tokenizer, which can use up to about 35% more tokens on the same input.

Agentic coding in large codebases

Anthropic cited more careful planning, longer agentic runs and more reliable work in big repositories than Opus 4.5.

Thinking your way

Use adaptive thinking with effort, or keep existing budget_tokens code running while you migrate.

Use cases

Pipelines that set temperature
Keep extraction, generation or evaluation jobs that depend on temperature or top_p running without rewrites.
Code review and debugging
Review changes and trace bugs across large codebases with adaptive thinking turned on.
Long-document analysis
Load contracts, filings or research sets into the 1M-token window and ask questions across all of them.
Stable eval baselines
Keep a fixed Opus 4.6 baseline to compare newer Opus models against on your own test sets.

Get started

Call Claude Opus 4.6 in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.

1
Create a key
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
Get your API key
2
Point your SDK at Zurelay
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1
3
Use claude-opus-4-6
Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.
claude-opus-4-6

Works with the tools you already use

Compare

Similar models. All on the same key.

64%off

Claude Opus 4.7

$1.78 / $8.93 per 1M tokens

Pick Claude Opus 4.7 for high-resolution vision and xhigh effort, once your code no longer sends sampling parameters or budget_tokens.

Claude Opus 4.7 API

52%off

Claude Opus 4.8

$2.40 / $12.00 per 1M tokens

Pick Claude Opus 4.8, the final Opus 4 release, for stronger bug finding and more honest reporting of uncertainty at the same list price.

Claude Opus 4.8 API

65%off

Claude Opus 5.5

$1.40 / $7.00 per 1M tokens

Pick Claude Opus 5.5, Anthropic's current Opus at a lower list price, for new projects.

Claude Opus 5.5 API

FAQ

Claude Opus 4.6 API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the Claude Opus 4.6 API cost on Zurelay?

Zurelay charges $2.40 per 1M input tokens and $12.00 per 1M output tokens, with cached input at $0.24. Anthropic's list price for Claude Opus 4.6 is $5.00 input and $25.00 output, so you save 52%. The rate is the same at every prompt length, and you pay from prepaid credit with no subscription.

Is there a cheaper Claude Opus 4.6 API than Anthropic's?

Yes. Zurelay serves claude-opus-4-6 at 52% below Anthropic's list price. It is the same model, not a smaller substitute. You keep your code and change the base URL and API key.

How do I get a Claude Opus 4.6 API key and use it with the OpenAI SDK?

Sign up at Zurelay, add prepaid credit and create a key in the dashboard. Set the OpenAI SDK base URL to https://api.zurelay.com/v1 and the model to claude-opus-4-6. The same key works for every other model in the catalog, and you can give it a monthly budget and a requests-per-minute cap.

Can I use Claude Opus 4.6 with the Anthropic SDK or Claude Code?

Yes. Set the Anthropic SDK base URL, or ANTHROPIC_BASE_URL for Claude Code, to https://api.zurelay.com with no /v1, because the client adds /v1/messages itself. Authenticate with your Zurelay key and select claude-opus-4-6. Prefilled assistant turns return an error on Opus 4.6, so steer output format with instructions or structured outputs instead.

What is the Claude Opus 4.6 context window?

Claude Opus 4.6 has a 1M-token context window and returns up to 128K output tokens per request. On its tokenizer, 1M tokens fits about 750k English words. Stream long responses so the connection stays open while tokens arrive.

When should I still use Claude Opus 4.6?

Use it when your code relies on temperature, top_p, top_k or budget_tokens thinking, which later Opus models reject, or when you need behavior that matches earlier Opus 4.6 results. It also needs fewer tokens than Opus 4.7 and later for the same text. For new projects, a newer Opus is the better starting point.

Is Claude Opus 4.6 deprecated?

No. As of September 2026, Anthropic lists Claude Opus 4.6 as an active legacy model, not deprecated, with retirement not sooner than February 5, 2027. Anthropic gives at least 60 days' notice before retiring a publicly released model. Testing a newer Opus now means a future retirement will not catch you out.

Does the Zurelay Claude Opus 4.6 API support streaming, and what are the limits?

Yes. Streaming is supported, and on chat completions you can set stream_options.include_usage to get token counts in the final chunk. Each key can carry its own monthly budget and requests-per-minute cap. If a route fails, Zurelay retries the request on another route, and failed requests are never billed.

Is Claude Opus 4.6 on Zurelay the same model as on Anthropic's API?

Yes. Requests to claude-opus-4-6 run on Claude Opus 4.6 itself, not a smaller or different model. Outputs are sampled, so exact wording can differ between calls on any API, including Anthropic's. Zurelay is an independent service and is not affiliated with or endorsed by Anthropic.

More models on Zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API key Talk to an engineer

Claude Opus 4.6 API

Claude Opus 4.6 API pricing. A fraction of the list price.

Claude Opus 4.6 API cost, worked out. And compared.

Chatbot

Documents

Coding agent

Classification

Where to buy Claude Opus 4.6

What is Claude Opus 4.6?

Where Claude Opus 4.6 shines. And what teams build with it.

Sampling parameters still work

Fewer tokens for the same text

Agentic coding in large codebases

Thinking your way

Pipelines that set temperature

Code review and debugging

Long-document analysis

Stable eval baselines

Call Claude Opus 4.6 in three steps.

Create a key

Point your SDK at Zurelay

Use claude-opus-4-6