ANTHROPIC · claude-opus-5-5
Claude Opus 5.5 API Pricing & Specs
Claude Opus 5.5 costs $2 per 1M input tokens and $10 per 1M output tokens through this API — 50% below Anthropic's list price of $4 / $20. It is the same upstream model, callable with one key on OpenAI-compatible and Anthropic protocols.
Official list price vs. your price
| Official list | Your price | You save | |
|---|---|---|---|
| Input · per 1M tokens | $4 | $2 | -50% |
| Output · per 1M tokens | $20 | $10 |
All prices in USD per 1M tokens.
Technical specs
- Vendor
- Anthropic
- Context window
- 200K tokens
- Max output tokens
- 128K tokens
- Modalities
- Text + image input + Image
Best for
- Repo-wide refactors and long coding runs
- Claude Code and long-lived agents
- The current Claude ceiling at 50% off
Start calling it in one line
Point any OpenAI-compatible client at the base URL below (Anthropic SDK: use the same host). The model id is the exact string to pass as the model parameter.
curl https://kktt.net/v1/chat/completions \
-H "Authorization: Bearer $KKTT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-opus-5-5", "messages": [{"role": "user", "content": "Hello"}]}'from openai import OpenAI
client = OpenAI(
api_key=os.environ["KKTT_API_KEY"],
base_url="https://kktt.net/v1",
)
resp = client.chat.completions.create(
model="claude-opus-5-5",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.KKTT_API_KEY,
baseURL: "https://kktt.net/v1",
});
const resp = await client.chat.completions.create({
model: "claude-opus-5-5",
messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);FAQ
How much does the Claude Opus 5.5 API cost?
Official list pricing is $4 per 1M input tokens and $20 per 1M output tokens. Through this API you pay $2 / $10 — a 50% discount, billed per token with no minimum spend.
Is this the same Claude Opus 5.5 model as Anthropic's official API?
Yes. Requests are routed to the same upstream Claude Opus 5.5 model — the discount comes from the gateway's billing rate, not from a different or quantized model.
Do I need a separate API key for Claude Opus 5.5?
No. One API key calls every GPT and Claude model on this platform, so you can switch models by changing the model parameter in the request — same base URL, same key.
Which clients can I use with Claude Opus 5.5?
Any OpenAI-compatible or Anthropic-protocol client: the official SDKs, Cursor, Cline, Roo Code, LibreChat, NextChat and others. Point the client's base URL at this API and use your key.