Claude Fable 5.1

anthropic/claude-fable-5.1
NewFeatured
VisionToolsJSONReasoning
by Anthropic · 2026-09-01

Claude Fable 5.1 is Anthropic's Mythos-class model — a capability tier above the Opus class — made safe for broad use, and the successor to Claude Fable 5. It improves on 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 engineering, and multi-step tasks where sustained coherence and judgment matter most. It accepts text, image, and file inputs with text output, serves a 1M-token context window with up to 128K output tokens, and supports adaptive reasoning and structured outputs. Fable 5.1 keeps the autonomous, long-horizon posture of the Fable line: it stays coherent across millions of tokens, improves its own outputs using file-based memory, and completes complex multi-step work with far less scaffolding than prior models. It is a strong default for AI coding assistants, deep research and analysis pipelines, and long-running autonomous agents.

ctx1M tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT8.01 s
INPUT$10.00/ 1M tokens
OUTPUT$50.00/ 1M tokens
p50 TTFT8.01 s7d
p95 TTFT10.00 s7d
TRAFFIC29.0Mtokens / 7d

Claude Fable 5.1 is an Anthropic model available on OrcaRouter with the model ID anthropic/claude-fable-5.1. It accepts text, image, and file inputs, supports a 1,000,000-token context window, and…

What is Claude Fable 5.1?

Who is Claude Fable 5.1 for?

What inputs and outputs are documented?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Anthropic SDKhttps://api.orcarouter.ai
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="anthropic/claude-fable-5.1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • stop
  • structured_outputs
  • tools
  • verbosity

Pricing

Pricing
Input / 1M tokens$10.00
Output / 1M tokens$50.00
Cache read / 1M$0.250
Cache write / 1M$12.50
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $220 · With prompt caching $186

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.0252

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
8.01 s
Output speed
61.1 tok/s
p95 TTFT
10.00 s
Error rate
5.4%

Public benchmarks

81.6
AA Coding
Better than 99% of models compared
#1 of 138
53.4
AA Intelligence
Better than 95% of models compared
#7 of 145
Artificial Analysis Intelligence Index
66.0
GPQA Diamond
93.7
Humanity's Last Exam
59.1
Long-Context Recall
85.3
SciCode
63.1
tau_banking
47.2
terminalbench_v2_1
91.4
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News1 mentions · 7ddown 5 vs the previous week

How it compares

Claude Fable 5.1Claude Fable 5Claude Opus 4.7Claude Opus 4.8
Input $/M$10.00$10.00$5.00$5.00
Output $/M$50.00$50.00$25.00$25.00
Context1.0M1.0M1.0M1.0M
Quality10/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What does Claude Fable 5.1 cost on OrcaRouter?
Input tokens are billed at $10.00 per 1,000,000 tokens and output tokens at $50.00 per 1,000,000 tokens. Those are Anthropic's provider rates, passed through on OrcaRouter with zero markup. No per-request fee or gateway surcharge is listed for this catalog entry.
What context window does Claude Fable 5.1 support?
It supports a context window of 1,000,000 tokens. That window includes all text, image, file, and chat history tokens sent as input. Its maximum output is 128,000 tokens per response, so a single request can consume a very large input while returning a long generated answer.
What are the key strengths of Claude Fable 5.1?
The supplied facts highlight three strengths: a 1,000,000-token context window, a 128,000-token output limit, and text, image, and file input support. The model records 66.0 on the Artificial Analysis Intelligence Index. On OrcaRouter it is billed at the provider rate with zero markup.
How does Claude Fable 5.1 compare with other models?
It positions itself as a large-context, high-output model. The only benchmark listed in the catalog is 66.0 on the Artificial Analysis Intelligence Index. For a fair comparison, run representative prompts against alternative models on OrcaRouter, measuring quality, latency, and cost per successful task. Smaller models may be cheaper for short workloads.
How is data handled when I use this model through OrcaRouter?
The catalog does not specify data retention practices for Claude Fable 5.1. Data is transmitted to Anthropic because Anthropic is the provider, and OrcaRouter handles the API route. Review Anthropic's privacy policy and OrcaRouter's data-handling documentation for retention, training, and regional details before sending sensitive files.
How do I call Claude Fable 5.1 through OrcaRouter's OpenAI-compatible API?
Set the base URL to https://api.orcarouter.ai/v1 and send a chat completion request with model set to anthropic/claude-fable-5.1. OrcaRouter authenticates the request with its own credentials. Use the standard messages and content structure from an OpenAI-compatible client. Inspect the usage field in the response for billed token counts.
What input formats does Claude Fable 5.1 support?
The catalog lists text, image, and file as the input modalities. Exact image pixel limits, acceptable file extensions, upload sizes, and token conversion costs are not provided. Test the file content format against OrcaRouter's API conventions. Audio is not listed as a supported input modality.
What is the maximum output length?
Claude Fable 5.1 can generate up to 128,000 tokens in a single response. That is an upper limit, not the amount it will produce for every prompt. Set max_tokens to a lower value to control cost and latency unless you specifically need very long output.

Embed this badge

Anthropic: Claude Fable 5.1$10.00/M in8014ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/anthropic/claude-fable-5.1" target="_blank"> <img src="https://www.orcarouter.ai/embed/anthropic/claude-fable-5.1.svg" alt="Anthropic: Claude Fable 5.1 on OrcaRouter" /> </a>
Markdown [![Anthropic: Claude Fable 5.1](https://www.orcarouter.ai/embed/anthropic/claude-fable-5.1.svg)](https://www.orcarouter.ai/models/anthropic/claude-fable-5.1)

Model card as data

GET /api/public/models/anthropic/claude-fable-5.1Open
Machine-readable:/llms.txt/llms-full.txt