Home → Pricing → claude-opus-5-5

Claude Opus 5.5 API pricing

claude-opus-5-5

Priced below Opus 5 on every line. The cache read rate is the one that matters for agent loops: a twentieth of the input price, where every other Claude model charges a tenth.

Claude You pay 45% of list price OpenAI-compatible Pay as you go
List price · input
$4.00
per 1M tokens · output $20.00
You pay · input
$1.80
per 1M tokens · output $9.00
You save 55% on every call. Same model, same context window, same speed — the only thing that changes is your bill.

Price breakdown

Per 1M tokensList priceAPICLANYou save
Input$4.00$1.8055%
Output$20.00$9.0055%

Cached input is billed at a fraction of the input rate, so agent tools that resend the same context — Codex, Claude Code, Cline — cost considerably less in practice than the raw token count suggests.

Cache reads list at $0.20 per million tokens (0.05x the input rate) and cache writes at $5.00 for the 5-minute cache. Batch requests are half the standard rate.

Work out your own cost

Put in the token counts from a typical request. Both columns update as you type.

At list price
—
At APICLAN
—

What a real session costs

A coding session through Codex on this platform used 90,459 tokens across five requests — roughly seventeen minutes of back-and-forth over a codebase. At list price that is $0.178. The customer paid $0.036.

That is real billing data, not an estimate. Heavy context reuse is exactly where the saving compounds: the same work, one fifth of the invoice.

How to call claude-opus-5-5

The API is OpenAI-compatible. Point your base URL at APICLAN and pass the model name — nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_KEY",
    base_url="https://apiclan.us/v1",
)

resp = client.chat.completions.create(
    model="claude-opus-5-5",
    messages=[{"role": "user", "content": "Hello"}],
)

Using Claude Code or the Anthropic SDK? Those clients append /v1/messages themselves, so their base URL is https://apiclan.us with no /v1. Full setup for every client is in the Quickstart.

Other Claude models

ModelInput / 1MOutput / 1M
claude-fable-5-1$4.50$22.50
claude-fable-5$4.50$22.50
claude-opus-5$1.12$5.62
claude-opus-4-8$1.12$5.62
claude-sonnet-5$0.450$2.25
claude-opus-4-7$1.12$5.62
claude-opus-4-6$1.12$5.62
claude-sonnet-4-6$0.675$3.38

Prices above are what you pay, not list price. Cheaper models in the same family often handle routine work at a fraction of the cost — worth testing before defaulting to the largest one.

Start using it

No subscription, no monthly minimum, no sales call. Top up with USDT and spend what you use — 1 USDT gives you 2 credits of API balance.

Read the 30-second quickstart

Pricing verified 2026-10-03 · calibrated against real invoices. List prices change; this page is regenerated automatically from live billing data.

Language: English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Deutsch · Français · Español · Türkçe · Português · Italiano · Bahasa Indonesia · Tiếng Việt · Bahasa Melayu · Polski · Čeština · فارسی · Русский