PL Log inCreate account
Launching in October 2026. Accounts, model catalog, calculator and docs are live. Studio is available in preview; generation is awaiting activation.

Chat & code Anthropic · 2026-09

Claude Fable 5.1 API

Anthropic's top generally available tier for hard reasoning and hours-long tasks

Input$10.80per 1M tokens
Output$54.00per 1M tokens

1,000 chatbot replies$37.801,500 input + 400 output tokens each

Cache reads on this model are billed at the input rate. Failed requests cost nothing.

Compare with other chat models →

Claude Fable 5.1 is Anthropic's model from September 2026 and sits in the tier above Claude Opus. It is the generally available version of the same model as Claude Mythos 5.1, with extra safeguards for biology and cybersecurity topics. In Jantaris it has a 1,000,000-token context window and up to 128K output tokens. Anthropic describes it as its strongest option for coding, knowledge work and problem solving that runs for hours across many tools, with the biggest gains over Fable 5 in agentic coding and long code refactors.

Best for

  • Research and analysis where a wrong answer is expensive
  • Agent workflows that run unattended for hours
  • Long refactors and front-end work across a large codebase
  • Security review of your own code, such as finding vulnerabilities
  • Hard problems where cheaper models have already failed your evals

How to call it

Use the OpenAI SDK with the Jantaris base URL:

python
from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="claude-fable-5.1",
    messages=[{"role": "user", "content": "Find the root cause of this race condition."}],
)
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

What is the Claude Fable 5.1 price per million tokens?

In Jantaris, Fable 5.1 costs $10.80 / $54.00 per 1M tokens. It is one of the most expensive chat models in the catalog, so check your token usage on a few real tasks before you move a whole pipeline to it.

Is Fable 5.1 worth it over Claude Opus 5.5?

Often not. Anthropic says Claude Opus 5.5 matches Fable 5.1 on most work at a lower cost. Keep Fable for the tasks where Opus 5.5 does not pass your tests.

Does Claude Fable 5.1 work with Claude Code?

Yes. Point ANTHROPIC_BASE_URL at https://jantaris.com, use your sk-jt- key and set the model to claude-fable-5.1. Anthropic runs Fable 5.1 at High effort by default in Claude Code, which means longer and more thorough answers.

How to call Claude Fable 5.1 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-fable-5.1",
    messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)