Claude Opus 5.5 API

Claude Opus 5.5 is the Opus model Anthropic released in September 2026, and the first one in the Claude 5.5 family. In Jantaris it comes with a 1,000,000-token context window and up to 128K output tokens per reply. Anthropic says it performs at the level of Claude Fable 5.1 on most work while costing less to run, and points to multi-step changes in large codebases, long agentic sessions and clearer writing that sticks to your style rules. Its knowledge cutoff is June 2026.

Best for

• Refactors and migrations that touch hundreds of files
• Coding agents in Claude Code that run for hours
• Reading a whole repository, spec or contract set in one request
• Technical writing that has to follow a house style guide

How to call it

Point the OpenAI SDK at Jantaris and pass the model id:

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="claude-opus-5.5",
    messages=[{"role": "user", "content": "Plan a Flask to FastAPI migration for this repo."}],
)
print(resp.choices[0].message.content)

It also works with the Anthropic SDK and Claude Code through /v1/messages, see the Claude Code guide.

FAQ

How much does the Claude Opus 5.5 API cost?

In Jantaris it costs $5.40 / $27.00 per 1M tokens. The amount comes off a prepaid balance that never expires, so there is no subscription and no monthly minimum.

Can I run Claude Opus 5.5 in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://jantaris.com, put your sk-jt- key in ANTHROPIC_AUTH_TOKEN and choose claude-opus-5.5 as the model. Give that key its own monthly spend limit in the dashboard, since long agent sessions send many requests.

Should I pick Opus 5.5 or Fable 5.1?

Start with Opus 5.5. Anthropic positions it at Fable 5.1 level for most tasks at a lower price, so Claude Fable 5.1 makes sense only when your own tests on Opus 5.5 still fall short. Note that thinking cannot be switched off on Opus 5.5.

How to call Claude Opus 5.5 via API

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="claude-opus-5.5",
    messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)

curl https://jantaris.com/v1/chat/completions \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-opus-5.5", "messages": [{"role": "user", "content": "Write a haiku about Baltic amber."}]}'

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://jantaris.com/v1", apiKey: process.env.JANTARIS_API_KEY });
const resp = await client.chat.completions.create({
  model: "claude-opus-5.5",
  messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);

export ANTHROPIC_BASE_URL=https://jantaris.com
export ANTHROPIC_AUTH_TOKEN=sk-jt-...
export ANTHROPIC_MODEL=claude-opus-5.5
claude