opendunes

Claude Fable 5.2

New

by AnthropicReleased 9 November 2026

#1 for reasoningThis model takes in text, images and files, keeps about 1,000 pages in mind at once, and writes replies of up to 120 pages of text. It is built for demanding technical work: sitting down to a long coding or reasoning job that other models of its line could not finish, and it thinks through each step before answering. Against its siblings, it trades a slightly shorter maximum reply for stronger gains in coding, reasoning and reading images. If your work is everyday short questions, a smaller or faster model in the same family may suit you better.

TakesTextImagesFiles
GivesText

Where your request runs

Four companies run this model. OpenDunes sends each request to one of them. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Google…
↑ Sent, per 1M
2 662,68 DA
↓ Back, per 1M
13 313,42 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Amazon Bedrock…
↑ Sent, per 1M
2 662,68 DA
↓ Back, per 1M
13 313,42 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Azure…
↑ Sent, per 1M
2 662,68 DA
↓ Back, per 1M
13 313,42 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Anthropic…
↑ Sent, per 1M
2 662,68 DA
↓ Back, per 1M
13 313,42 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Anthropic · Fast…
↑ Sent, per 1M
5 325,37 DA
↓ Back, per 1M
26 626,85 DA
Cache read
133,13 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Google2 662,68 DA13 313,42 DA66,57 DA………
Amazon Bedrock2 662,68 DA13 313,42 DA66,57 DA………
Azure2 662,68 DA13 313,42 DA66,57 DA………
Anthropic2 662,68 DA13 313,42 DA66,57 DA………
Anthropic · Fast5 325,37 DA26 626,85 DA133,13 DA………

Also charged: writing to the cache ↑ 3 328,36 · a web search 3,33 DA each.

You pay the price of the provider that served your request. Prices read 02:47 · speed over the last 30 minutes · uptime over 3 days.

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 9,32 DA per message3 000 DA buys about 320 messages

One message, the ordinary use

1 000 sent1 000 tokens sent× 2 662,68 per 1M× 2 662,68 DA per 1M2,66 DA
500 back500 tokens back× 13 313,42 per 1M× 13 313,42 DA per 1M6,66 DA
Total≈ 9,32 DA

Every rate

Meter↑ you send↓ comes back
Text tokens2 662,68 DA13 313,42 DA
Cached tokens read66,57 DA
Cache-write tokens3 328,36 DA
1-hour cache-write tokens5 325,37 DA

per 1M tokens

Web search · 3,33 DA per call

Everyday jobs, priced

Draft a full technical report from a folder of long documents≈ 79,88 DA
Answer detailed questions about a book-length contract with charts≈ 93,19 DA
Turn a set of design screenshots into working interface code≈ 213,01 DA
Review a whole codebase and rewrite the parts that need fixing≈ 266,27 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
Add creditDeposits from 100 DA, withEdahabiaCIB

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Understands images
You send

What's the total on this invoice, and when is it due?

invoice-scan.jpg · photoTry in Chat Lab
Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txtTry in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
anthropic/claude-fable-5.2
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="anthropic/claude-fable-5.2",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokensstop

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Other

Also accepted by this model.

max_completion_tokensverbosity

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
1 000 000 tokens
Max output
128 000 tokens
Reads at once
≈ 1 000 pages
Longest reply
≈ 96 000 words
Tokenizer
Claude
Released
9 Nov 2026
Full API reference

Questions about Claude Fable 5.2

How much does Claude Fable 5.2 cost in dinars?

About 9,32 DA per message. ↑ 2 662,68 DA · ↓ 13 313,42 DA per 1M tokens.

Is Claude Fable 5.2 free? Can I try it?

No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.

What is Claude Fable 5.2 best for?

#1 for reasoning · This model takes in text, images and files, keeps about 1,000 pages in mind at once, and writes replies of up to 120 pages of text. It is built for demanding technical work: sitting down to a long coding or reasoning job that other models of its line could not finish, and it thinks through each step before answering. Against its siblings, it trades a slightly shorter maximum reply for stronger gains in coding, reasoning and reading images. If your work is everyday short questions, a smaller or faster model in the same family may suit you better.

Claude Fable 5.2 or Claude Fable 5.1?

Claude Fable 5.1 costs 2,33 DA more for the same message.

How do I pay for Claude Fable 5.2 without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Claude Fable 5.2 included, is paid from that balance. No foreign card, no conversion.

Does Claude Fable 5.2 work in Arabic, French or Darja?

Anthropic names no languages for Claude Fable 5.2. Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

It reads text, images and PDFs. Up to 1M tokens in one request, about 1 000 pages. It writes up to 96 000 words at once.

Is Claude Fable 5.2 open source?

No. Anthropic has not published its weights.

Who makes Claude Fable 5.2, and when was it released?

Anthropic. Released 9 November 2026.

Other Anthropic models, priced in dinars

See all Anthropic models
Claude Opus 5.5Anthropic · Sep 22, 2026

#1 for mobile apps · Claude Opus 5.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages, with an effort setting as the main dial between depth and speed. Give it edits that span a large codebase, bug hunts, financial or scientific analysis, and charts, diagrams or screenshots full of detail. It needs fewer steps and less output than Opus 5 for the same job and reports back in plainer language. For harder reasoning, Anthropic points to Fable 5.1; for lighter work, Sonnet 5.5.

Searches the webThinks firstUses your tools
≈4,66 DAper message
View model
Claude Haiku 5.5Anthropic · Oct 7, 2026

Haiku 5.5 is the quick, small Claude for high-volume work: summarising, sorting, pulling out details, routing, driving a web browser and acting as a helper agent. It reads text, images and files, keeps about 1,000 pages in mind, replies up to about 128 pages, and has an effort setting while deciding for itself how long to think. It succeeds Haiku 4.5, with better coding and computer use.

Searches the webThinks firstUses your tools
≈0,12 DAper message
View model
Claude Sonnet 5.5Anthropic · Sep 28, 2026

#1 for interface design · Claude Sonnet 5.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages, with thinking always on and an effort setting as the main dial. It is Anthropic's pick for well-defined daily jobs: shipping a feature, fixing a bug, or turning notes into finished reports, slide decks and spreadsheets. Lower effort keeps it responsive in agents that work step by step. For high-volume sorting and extraction, Haiku 5.5 is faster; for long, hard projects, Opus 5.5.

Searches the webThinks firstUses your tools
≈2,33 DAper message
View model
Claude Sonnet 5Anthropic · Jun 30, 2026

#8 for games · Claude Sonnet 5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. It decides for itself how long to think, and you set the effort from low to extra high. Use it for coding, agents that work through a task on their own, and professional work such as documents and analysis; it stops some dangerous requests as they happen.

#20 of 118 for codingSearches the webThinks first
≈2,33 DAper message
View model