How much does Claude Fable 5.1 cost?

On the Respan gateway, Claude Fable 5.1 costs from $5.00 per 1M input tokens and $25.00 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 7 routes from 5 providers, it costs $9.43 per 1M input tokens and $47.14 per 1M output tokens.

Which providers serve Claude Fable 5.1 on Respan?

Claude Fable 5.1 is available through 7 routes from 5 providers: OpenRouter, Anthropic, Bedrock, Perplexity, and Google Vertex AI. Bedrock and Google Vertex AI require your own provider API key (BYOK).

What is Claude Fable 5.1's context window?

Claude Fable 5.1 accepts up to 1M tokens of context on its largest provider route.

How do I use Claude Fable 5.1 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "anthropic/claude-fable-5-1". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Claude Fable 5.1?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Anthropic at 45 tokens per second, and the lowest response latency was 4.1 seconds on Perplexity. Speed varies with request size and provider.

Where does Claude Fable 5.1 rank on the Respan Index?

Claude Fable 5.1 scores 69.2 out of 100 on the Respan Index v1.1, ranking #5 of 143 models. By category: Coding 69.5, Agents 73.4, Reasoning 70.2, Knowledge & language 71.5, and Human preference 58.8. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Claude Fable 5.1 score on benchmarks?

Claude Fable 5.1 has 32 published benchmark scores, including WeirdML 92.9%, APEX-Agents 68.6%, and LiveBench Reasoning 91.7%. Each score links to where it was published; the data is collected by llmmetric.com.

Claude Fable 5.1

Q: What is Claude Fable 5.1?

Claude Fable 5.1 is a model from Anthropic, released on Sep 1, 2026. 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 such as long code refactors.

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 such as long code refactors.

Input / output, from: $5.00 / $25.00 per 1M
Weekly tokens / requests: 1M / 134
Context: 1M tokens
Released: Sep 1, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "anthropic/claude-fable-5-1".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="anthropic/claude-fable-5-1",

    messages=[{"role": "user", "content": "Hello!"}],

)

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

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

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);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "anthropic/claude-fable-5-1",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

7 routes from 5 providers, cheapest first, priced per 1M tokens after gateway discounts. BYOK routes use your own key.

Provider	Context	Input	Output	Cache read	Capabilities
OpenRouter`openrouter/anthropic/claude-fable-5.1:batch`	1M	$5.00/M	$25.00/M	$0.13/M	+2
Anthropic`anthropic/claude-fable-5-1`	1M	$10.00/M	$50.00/M	$0.25/M	+2
BedrockBYOK only`bedrock/global.anthropic.claude-fable-5-1`	1M	$10.00/M	$50.00/M	$0.25/M	+2
OpenRouter`openrouter/anthropic/claude-fable-5.1`	1M	$10.00/M	$50.00/M	$0.25/M	+2
Perplexity`perplexity/anthropic/claude-fable-5-1`	1M	$10.00/M	$50.00/M	$0.25/M
Google Vertex AIBYOK only`vertex_ai/claude-fable-5-1@default`	1M	$10.00/M	$50.00/M	$0.25/M	+2
BedrockBYOK only`bedrock/us.anthropic.claude-fable-5-1`	1M	$11.00/M	$55.00/M	$0.28/M	+2

Is a provider down? OpenRouter status, Anthropic status, AWS Bedrock status, Perplexity status, Google AI status

Pricing

Averaged across 7 routes from 5 providers, in USD per 1M tokens after gateway discounts.

Average input: $9.43 per 1M
Average output: $47.14 per 1M
Average cache read: $0.24 per 1M
Average cache write: $11.79 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$11.00/MBedrockLowest$5.00/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway, 3 of 7 routes had traffic in that window. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

45tokens/sbest, on Anthropic

Faster than 60% of the other 484 models on the gateway

Anthropic45 tok/s
Perplexity1.0 tok/s

Time to first token

Lower is better

4.4sbest, on OpenRouter

Faster than 19% of the other 62 models on the gateway

OpenRouter4.4 s
Anthropic7.0 s

Response latency

Lower is better

4.1sbest, on Perplexity

Faster than 18% of the other 499 models on the gateway

Perplexity4.1 s
Anthropic7.3 s

No traffic in the last 30 days on OpenRouter, Bedrock, and Google Vertex AI.

Benchmarks

The Respan Index plus 32 published scores from 11 sources, each linked to where it was published.

69.2/ 100

Respan Index#5 of 143

143 ranked models. The shaded band is this model's 95% interval, 65.0 to 73.0. GPT-6.1 Sol and Claude Sonnet 5.5 fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
WeirdMLHåvard Tveit Ihle	92.9%	Håvard Tveit Ihle	Oct 5, 2026
GSO Opt@1GSO	87.3%	GSO	Sep 27, 2026
LiveBench CodingLiveBench	86.4%	LiveBench	Oct 5, 2026
CursorBench 3.2.0Anthropic	73.4%	Anthropic	Sep 1, 2026
MirrorCodeEpoch AI	73.3%	Epoch AI	Oct 5, 2026
Terminal-Bench 4.0Vals AI	58.1%	Vals AI	Oct 5, 2026
FrontierSWE V2Proximal Labs	56.3%	Proximal Labs	Oct 5, 2026
Terminal-Bench Science 0.1Anthropic	52.6%	Anthropic	Sep 1, 2026

Benchmark	Score	Source	Published
APEX-AgentsMercor	68.6%	Mercor	Oct 5, 2026
LiveBench Agentic CodingLiveBench	66.1%	LiveBench	Oct 5, 2026
Vending-Bench 2Andon Labs	5421.56 · #25 of 59	Andon Labs	Oct 5, 2026
GDPval-AA v2Anthropic	1853 Elo · #1 of 8	Anthropic	Sep 1, 2026

Benchmark	Score	Source	Published
LiveBench ReasoningLiveBench	91.7%	LiveBench	Oct 5, 2026
SimpleBenchSimpleBench	86.6%	SimpleBench	Sep 3, 2026
LiveBench Data AnalysisLiveBench	80.3%	LiveBench	Oct 5, 2026
Humanity's Last Exam (no tools)Anthropic	60.9%	Anthropic	Sep 1, 2026
Mystery Game PuzzlesEpoch AI	58%	Epoch AI	Oct 5, 2026
EBR-benchEpoch AI	57.1%	Epoch AI	Oct 5, 2026
Chess PuzzlesEpoch AI	47%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	100%	Epoch AI	Oct 5, 2026
LiveBench MathematicsLiveBench	97%	LiveBench	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	90.2%	Epoch AI	Oct 5, 2026
FrontierMath Tier 4 v2Epoch AI	87.8%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LiveBench LanguageLiveBench	89.5%	LiveBench	Oct 5, 2026
LiveBench Instruction FollowingLiveBench	73%	LiveBench	Oct 5, 2026
SimpleQA VerifiedEpoch AI	70.8%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
Furniture AssemblyEpoch AI	70%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1744 Elo · #5 of 99	LMArena	Oct 8, 2026
LMArena EloLMArena	1501 Elo · #6 of 147	LMArena	Oct 8, 2026
LMArena VisionLMArena	1286 Elo · #15 of 85	LMArena	Oct 9, 2026
LMArena AgentLMArena	0.1174 · #6 of 51	LMArena	Oct 12, 2026