How much does Claude Fable 5.2 cost?

Claude Fable 5.2 costs $8.00/M input tokens and $40.00/M output tokens, with separate rates for Cache Read at $0.20/M tokens, Cache Write at $10.00/M tokens, and Cache Write (1h) at $16.00/M tokens.

What is the context length of Claude Fable 5.2?

Claude Fable 5.2 has a 1,000,000 token context window. It supports up to 128,000 completion tokens.

Does Claude Fable 5.2 support tool calling and structured outputs?

Yes. Claude Fable 5.2 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Claude Fable 5.2 support?

Claude Fable 5.2 accepts text, images, and files such as PDFs as input and returns text.

Which providers serve Claude Fable 5.2?

Claude Fable 5.2 is served by 4 providers on OpenRouter: Google Vertex, Amazon Bedrock, Azure, and Anthropic. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Claude Fable 5.2 released?

Claude Fable 5.2 was released on November 9, 2026.

By using Claude Fable 5.2, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. Learn more

Amazon Bedrock endpoint is BYOK-only while we work on enabling public access.

Anthropic: Claude Fable 5.2

anthropic/claude-fable-5.2

Compare

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible software migrations, designed working electronic devices from scratch, and made progress on open problems in physics and mathematics. It communicates more clearly than earlier Fable models and generates output up to 30% faster than Fable 5.1. Adaptive extended thinking is always on, with reasoning effort levels from low to max (default high) and preserved thinking across turns. Anthropic recommends Opus 5.5 as the daily driver for most coding and knowledge work, with Fable 5.2 for the most ambitious, open-ended problems.

Modalities

In / out price

$8 / $40per 1M

Context

1.0M

Released

Nov 9, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$8.00	$40.00	$0.20	4.52s	81 tok/s	98.90%
	$8.00	$40.00	$0.20	4.20s	83 tok/s	99.88%
	$8.00	$40.00	$0.20	4.91s	83 tok/s	99.09%
BYOK only	$8.00	$40.00	$0.20	6.24s	85 tok/s	--
Not used in Standard routing:Why these endpoints are not used
Fast	$16.00	$80.00	$0.40	1.66s	204 tok/s	100.00%

Input $8.00Output $40.00
81 tok/s98.90% uptime
Input $8.00Output $40.00
83 tok/s99.88% uptime
Input $8.00Output $40.00
83 tok/s99.09% uptime
Input $8.00Output $40.00
BYOK only
85 tok/s-- uptime
Not used in Standard routing:Why these endpoints are not used
Input $16.00Output $80.00
Fast
204 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$1.423/M tokens

Output

$40.58/M tokens

Claude Fable 5.2 — Price history

Price history

No effective price data for this selection

		$1.31	$40.00	87.7%	61.7%
		$1.33	$40.00	88.4%	1.1%
		$1.62	$40.00	87.3%	25.6%
		$1.76	$40.00	82.6%	8.9%
Not used in Standard routing:Why these endpoints are not used
	Fast	$1.12	$80.00	96.3%	2.6%

Effective in $1.31Effective out $40.00
Token share
61.7%
Effective in $1.33Effective out $40.00
Token share
1.1%
Effective in $1.62Effective out $40.00
Token share
25.6%
Effective in $1.76Effective out $40.00
Token share
8.9%
Not used in Standard routing:Why these endpoints are not used
Effective in $1.12Effective out $80.00
FastToken share
2.6%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.62%

Availability over the last 3 days

Last 72 hours

Availability 99.62%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

98.92%

Without Routing

91.41%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Anthropic: Claude Fable 5.2 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) Intelligence Index	64.6
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) HLE	74.3%
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) AA-LCR	83.3%
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) GDPval-AA	66.6%
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) CritPt	35.4%
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) SciCode	67.7%
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) AA-Omniscience Accuracy	79.1%
Artificial Analysis	Claude Fable 5.2 (Max, Default Fallback) AA-Omniscience Non-Hallucination Rate	40.7%
Design Arena	Claude Fable 5.2 Agents Arena Full Stack Elo	1402
Design Arena	Claude Fable 5.2 Agents Arena Mobile Apps Elo	1325
Design Arena	Claude Fable 5.2 Agents Arena Pdf Elo	1309
Design Arena	Claude Fable 5.2 Agents Arena Spreadsheet Elo	1434
Design Arena	Claude Fable 5.2 Models Arena 3D Elo	1513
Design Arena	Claude Fable 5.2 Models Arena Code Categories Elo	1373
Design Arena	Claude Fable 5.2 Models Arena Game Development Elo	1396
Design Arena	Claude Fable 5.2 Models Arena UI Component Elo	1368
Design Arena	Claude Fable 5.2 Models Arena Website Elo	1353
Vals AI	Claude Fable 5.2 BioMysteryBench	83.7%
Vals AI	Claude Fable 5.2 Code Migration v1.1	83.3%
Vals AI	Claude Fable 5.2 EMB v1.1	77.4%
Vals AI	Claude Fable 5.2 Finance Agent v2.1	69.5%
Vals AI	Claude Fable 5.2 Vals Finance Index	63.6%
Vals AI	Claude Fable 5.2 HLAB-Vals-1.1	5.0%
Vals AI	Claude Fable 5.2 Immigration	74.0%
Vals AI	Claude Fable 5.2 Vals Legal Index	69.2%
Vals AI	Claude Fable 5.2 Legal Research Bench	46.2%
Vals AI	Claude Fable 5.2 MysteryMechanism	51.8%
Vals AI	Claude Fable 5.2 ProgramBench	19.0%
Vals AI	Claude Fable 5.2 ProofBench v1.1	100.0%
Vals AI	Claude Fable 5.2 Vals RSI Index	37.9%
Vals AI	Claude Fable 5.2 Vals Science Index	63.7%
Vals AI	Claude Fable 5.2 SWE-bench Multimodal	62.3%
Vals AI	Claude Fable 5.2 Tax Agent Bench	32.1%
Vals AI	Claude Fable 5.2 Terminal-Bench 4.0	65.2%
Vals AI	Claude Fable 5.2 Terminal-Bench-Science	55.7%
Vals AI	Claude Fable 5.2 Vals Index	71.3%
Vals AI	Claude Fable 5.2 Vibe Code Bench v1.1	93.8%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

274Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

50.7Btokens

There are many coding agents, but this one is yours.

16.5Btokens

omp

new

9.99Btokens

bcode

new

7.18Btokens

Rest of OpenRouter

14.9B

Top 5 Apps

14.6B

Anthropic: Claude Fable versions

Not currently available through EU in-region routing. In-region routing docs

More models from Anthropic

Claude Fable 5.2 (batch)

Text1M context$4 / $20

Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.

It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.

Text1M context$0.10 / $0.50

Claude Haiku 5.5 (batch)

Text1M context$0.05 / $0.25

Claude Sonnet 5.5

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$2 / $10

Claude Sonnet 5.5 (batch)

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$1 / $5

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

Text1M context$4 / $20

Claude Opus 5.5 (batch)

Text1M context$2 / $10

Claude Fable 5.1

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 code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

Text1M context$10 / $50

Claude Fable 5.1 (batch)

Text1M context$5 / $25

Claude Opus 5

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 5 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$5 / $25

Claude Opus 5 (batch)

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$2.50 / $12.50

Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

Text1M context$2 / $10

Claude Sonnet 5 (batch)

Text1M context$1 / $5

Claude Fable Latest

This model always redirects to the latest model in the Claude Fable family.

Text1M context

Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

Text1M context$10 / $50

Claude Fable 5 (batch)

Text1M context$5 / $25

Claude Opus 4.8

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 4.8 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

Text1M context$5 / $25

Claude Opus 4.8 (batch)

Text1M context$2.50 / $12.50

Anthropic: Claude Fable 5.2

Providers