What is the Claude Opus 5 context window?

Anthropic documents a one-million-token context window and a 128k-token maximum output for Claude Opus 5. Thinking tokens count toward the output limit, so a long reasoning pass shares the same budget as the visible answer.

Does Claude Opus 5 think by default?

Yes. Omitting the thinking parameter runs adaptive thinking on Claude Opus 5, which is a change from the previous Opus generation where omitting it meant no thinking. If you carried a tight max-token budget over from that generation, raise it or responses can truncate.

Can I turn thinking off on Claude Opus 5?

Only at effort high or lower. Pairing disabled thinking with xhigh or max effort is rejected, and the check runs on every request rather than once per conversation. Given how well Claude Opus 5 performs at low and medium effort, lowering effort is usually the better lever than disabling thinking.

Does Claude Opus 5 accept temperature and top_p?

No. The sampling parameters were removed on this generation and sending them is rejected. Steer Claude Opus 5 with prompting and the effort level instead. Fixed thinking-token budgets and last-assistant-turn prefills are also no longer accepted.

How does Claude Opus 5 compare with Claude Opus 4.8?

Anthropic lists the same published price, the same one-million-token context window and the same 128k output ceiling for both. What changed is the capability tier plus two request-surface defaults: thinking is on by default on Claude Opus 5, and disabling it is capped at high effort. The prompt-cache minimum also halves.

Which endpoint does Claude Opus 5 use on reAPI?

An OpenAI-compatible `/v1/chat/completions` endpoint on api.reapi.ai, with `claude-opus-5` as the model string. Anthropic's alias carries no date suffix, so the model id you send is exactly that.

What is the Claude Opus 5 knowledge cutoff?

Anthropic lists both the training data cutoff and the reliable knowledge cutoff for Claude Opus 5 as May 2026. For anything newer than that, give Claude Opus 5 web search or supply the material in the request.

Is Claude Opus 5 free or paid?

Paid. Usage is billed pay-as-you-go in USD from your api.reapi.ai token balance, based on input, output, and any applicable cache-token rates. See the live per-1M-token rates in the pricing table on this page; failed requests are not charged.

Does Claude Opus 5 require a monthly subscription?

No. There is no monthly subscription. Add funds to your api.reapi.ai token balance and pay in USD only for the input, output, and any applicable cache tokens each request uses. The live per-1M-token rates are in the pricing table on this page.

How do I get a Claude Opus 5 API key?

Sign up at api.reapi.ai and create a key under API Keys, then pass it as a Bearer token in the Authorization header. Chat keys and their token balance are separate from the reapi.ai image and video gateway.

Claude Opus 5 — 1M Context, Agentic Coding

Claude Opus 5 is Anthropic's model for complex agentic coding and enterprise work. Claude Opus 5 reads a 1M-token context window, writes up to 128k tokens back, and runs adaptive thinking on by default with an effort dial from low through max. On reAPI, Claude Opus 5 bills at less than half Anthropic's published per-token rate on both input and output.

Highlights: Extended thinking · tool use · structured output
Best for: Hard reasoning, agent workflows
Input: Chat messages (OpenAI-compatible)
Output: Text, streaming optional

Claude Opus 5modelclaude-opus-5

Claude Opus 5 playground

Chat models run on the api.reapi.ai gateway, which has its own console and its own key. Open the console to run Claude Opus 5 through the OpenAI-compatible Chat Completions surface.

Open console Token rates

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost

$0.014414.4 credits

One 1K-token prompt with a 1K-token answer at the cheapest tier.

Testing budget guide

Add credits

$10

≈ 694 tests

$50

≈ 3472 tests

$100

≈ 6944 tests

Input: $2.4; Price · 1M tokens
Output: $12.0; Price · 1M tokens

What is the Claude Opus 5 API?

Claude Opus 5 is Anthropic's model for complex agentic coding and enterprise work, served on an OpenAI-compatible /v1/chat/completions endpoint. It gives you a 1M-token context window, up to 128k output tokens per call with thinking tokens counted inside that budget, adaptive thinking that is on by default, and a five-level effort dial — low, medium, high, xhigh, max — that takes the place of the sampling knobs, since temperature, top_p and top_k are rejected on this model. Usage is billed per million tokens, with input and output priced separately.

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Claude Opus 5 working through a multi-file code change in one session

Long-horizon agentic coding that finishes the job

Anthropic positions Claude Opus 5 for complex agentic coding and enterprise work, and the shape of the model matches that: a 1M-token context window means a whole repository, its tests and its issue history fit in one request, and 128k output tokens is room for a multi-file change rather than a stub. Adaptive thinking is on by default, so Claude Opus 5 holds a plan together across tool calls instead of restarting its reasoning each turn. The practical advice from Anthropic's own migration guidance is to give Claude Opus 5 the complete task specification up front in a single well-specified turn and let it run, rather than revealing the task across many short interactive turns.

Read the API docs

Claude Opus 5 reviewing a pull request and reporting findings with severity

Code review and debugging with the filter turned off

Claude Opus 5 finds real bugs at high precision and high recall, and it stays accurate at lower effort — which makes a cheap fast pass at review time plus a thorough pass later a practical pattern. One caveat worth designing around: Claude Opus 5 follows severity instructions literally. A review prompt that says only report high-severity issues will get exactly that, and your measured recall drops even though the underlying bug-finding improved. Ask Claude Opus 5 to report everything with a confidence level and a severity, then filter in a separate pass.

Claude Opus 5 reading a large document set and producing a structured deliverable

Whole-document enterprise work without a chunking layer

Text, images and PDF are all inputs to Claude Opus 5, and the million-token window is large enough that a contract set, a research bundle or a year of filings goes in whole. That removes the retrieval layer whose only job was working around a small context. Claude Opus 5 also generates and edits complex multi-sheet spreadsheets with real formulas and builds slide decks that follow design conventions, and it can be told to follow a specific template when one is required. Vision is strong enough on charts and dense documents that giving Claude Opus 5 tools to crop and re-examine its own output beats simply raising the thinking depth.

Why reAPI for Claude Opus 5

Under half the published rate

Anthropic publishes a per-million-token rate for Claude Opus 5 input and output. On reAPI, Claude Opus 5 bills at less than half of both — no subscription underneath it, no minimum commitment, pay-as-you-go in USD against your gateway balance. The exact numbers are in the pricing table on this page.

OpenAI-compatible drop-in

Claude Opus 5 is served from a standard `/v1/chat/completions` endpoint. If your code already speaks that shape, adopting Claude Opus 5 is a base URL, a key and a model string — the same SDKs work once the base URL points at the gateway. No SDK swap, no bespoke client.

One key across Claude, GPT and Gemini

The same api.reapi.ai key that calls Claude Opus 5 calls the GPT and Gemini families too. Comparing Claude Opus 5 against another frontier model, or failing over when one provider has a bad hour, is a model string rather than a second integration, a second invoice and a second set of credentials.

Claude Opus 5 vs Claude Opus 4.8

This comparison is not about price. Anthropic publishes the same per-token rate, the same one-million-token context window and the same 128k output ceiling for both models. Claude Opus 5 is the capability step-change on top of that, and it quietly changes two request-surface defaults that will break code carried straight over — thinking now runs by default, and turning it off is capped at high effort.

Capability

Claude Opus 5 on reAPI

Claude Opus 4.8

Anthropic's positioning

For complex agentic coding and enterprise work; the current Opus generation

The most capable model of the Opus 4 series, now the previous generation

Published rate

Identical published per-token rate — and less than half of it on reAPI

Identical published per-token rate

Context and output limits

1M-token context, 128k max output

Identical — 1M-token context, 128k max output

Thinking default

On — omitting the thinking parameter runs adaptive thinking

Off — adaptive thinking has to be set explicitly

Disabling thinking

Accepted only at effort high or lower; rejected at xhigh and max

Accepted at any effort level

Prompt-cache minimum

512-token minimum cacheable prefix, so shorter prompts now cache

1024-token minimum — twice as long a prefix before caching starts

Comparison reflects behavior documented on Anthropic's own model-overview page at the time of writing. Rates are described as relationships rather than amounts; the live numbers for Claude Opus 5 are in the pricing table above.

Ship Claude Opus 5 in three steps

step 01
Create an account and key on api.reapi.ai
Sign up at api.reapi.ai, open the console and generate an API key. That one key reaches Claude Opus 5 and every other model on the gateway, billed from a single balance.
Open
step 02
Point your client at the gateway
Set your base URL to api.reapi.ai and your key to the one you just created. Any client that already speaks OpenAI Chat Completions works unchanged — no SDK swap is needed to reach Claude Opus 5.
Open
step 03
Send `claude-opus-5` as the model
Set the model field to `claude-opus-5` and post your messages. Turn on streaming for long outputs, and remember that Claude Opus 5 thinks by default, so leave room in max tokens for the reasoning as well as the answer.
Open

docs/api/claude-opus-5

API reference

Drop-in code and the full parameter table.

View full reference

curl https://api.reapi.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "group": "default",
    "messages": [
      { "role": "user", "content": "Hello" }
    ],
    "stream": true,
    "max_tokens": 16000
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

Claude Opus 5 is billed pay-as-you-go in USD per token against your api.reapi.ai balance, with separate input and output rates and no subscription. Both rates sit at less than half Anthropic's published per-token rate. Current numbers are in the pricing table on this page.