Hormouz AIHormouzSign in

Anthropic: Claude Fable 5.1: AI model

Claude Fable 5.1 is an upgraded Claude model for agentic coding and knowledge work from Anthropic with a 1M-token context window. Reachable from inside Iran through Hormouz.

Context window:
1,000,000 tokens
Input:
$10/1M tokens
Output:
$50/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels: Always thinks · max · xhigh · high · medium · low

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the largest gains in agentic coding, long-running agent workflows and knowledge work, especially long refactors, front-end and visual code, and finance and analysis. Its plans and summaries are shorter and clearer than Fable 5's. It is meant as a drop-in upgrade for Fable 5 and is worth testing alongside Opus on reasoning-heavy work.

It accepts text, image and file (PDF) input and returns text, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting. Claude Fable 5.1 is commonly used for long code refactors, front-end development, agent workflows, financial analysis and knowledge work. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.

Pricing is usage-based: $10 per million input tokens and $50 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-fable-5.1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorAnthropic
TypeText, Image
Context window1,000,000 tokens
Pricing$10.00/M in · $50.00/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

53.4
Intelligence Index
Better than 97% of models we compared
81.6
Coding Index
Better than 99% of models we compared
57.9
Agentic Index
Better than 99% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
93.7%
HLE
Humanity's Last Exam
59.1%
AA-LCR
Long-context reasoning
85.3%
CritPt
Research-level physics reasoning
29.7%
AA Omniscience
Broad factual knowledge accuracy
67.2%
Non-Hallucination
Rate of avoiding fabricated answers
27.4%

Coding

SciCode
Python for scientific computing
63.1%

Agentic

GDPval
Economically valuable tasks
62.9%

Source: Artificial Analysis

Full-Stack
Top 2%
1,325Elo
Win rate: 57.2%
Godot Game Dev
Top 3%
1,327Elo
Win rate: 60.7%
Mobile Apps
Top 9%
1,261Elo
Win rate: 55.5%
Python Slides
Top 4%
1,328Elo
Win rate: 62.6%
Web Apps
Top 2%
1,310Elo
Win rate: 56.1%
3D
Top 2%
1,404Elo
Win rate: 67.8%Avg time: 304s
ASCII Art
Top 4%
1,333Elo
Win rate: 65%Avg time: 188s
Code
Top 3%
1,342Elo
Win rate: 59.3%Avg time: 323s
Data Viz
Top 3%
1,352Elo
Win rate: 61.8%Avg time: 243s
Game Dev
Top 1%
1,394Elo
Win rate: 65.6%Avg time: 381s
SVG
Top 5%
1,307Elo
Win rate: 57.1%Avg time: 79.5s
UI Component
Top 6%
1,345Elo
Win rate: 59.6%Avg time: 216s
Website
Top 4%
1,320Elo
Win rate: 56.3%Avg time: 323s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-fable-5.1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="anthropic/claude-fable-5.1",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "anthropic/claude-fable-5.1",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Anthropic: Claude Fable 5.1 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Anthropic: Claude Fable 5.1 and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an accountBuy Claude API access, paid in rial

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Claude Fable 5.1 cost?
Pricing is usage-based: $10 per million input tokens and $50 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
How do I access Claude Fable 5.1 from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Claude Fable 5.1 compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does Claude Fable 5.1 have?
It has a 1M-token context window, accepts text, image and file (PDF) input, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting.
What is Claude Fable 5.1 good for?
Typical uses are long code refactors, front-end development, agent workflows, financial analysis and knowledge work.
Claude Fable 5.1 or GPT-6 Astra: which should I use?
Both are top-tier models at the same price per token. Fable 5.1 is especially strong at long refactors, front-end code and finance work; GPT-6 Astra is OpenAI's flagship for the hardest reasoning and professional tasks. Compare their benchmarks side by side on our comparison page and test both on your own prompts.

Updated 2026-10-13