Primary use stated or inferred cautiously from official documentation.
A
ANTHROPIC / claude-fable-5-1
Claude Fable 5.1
Long-running reasoning and agents.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | claude-fable-5-1 |
|---|---|
| Model type | Text and reasoning |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | SEP 2026 |
| Knowledge cutoff | JUN 2026 |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 1,000,000 tokens |
| maximum output | 128,000 tokens |
| Reasoning | Adaptive thinking always active |
| Published tools | Use of tools · Web search · Code execution · Computer use |
| Structured Outings | Supported |
| Batch processing | Compatible · 50% discount |
| Prompt cache | Compatible · up to 90% savings on reads |
| Fine-tuning | Not published |
| Verified platforms | Claude.ai · Claude API · Amazon Bedrock · Google Cloud · Microsoft Foundry |
Long-running reasoning and agents.
Cost and performance depend on the reasoning level.
03 / CAPABILITIES
What it can do
Orientation
Long-running reasoning and agents.
Context
1.000.000 tokens · 128.000 tokens
Tools and integration
Tool use · Web search · Code execution · Computer use
Access
Claude, Claude API and associated clouds
Input modalities
TextImage
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 10.00 USD / 1 M tokens | Standard API rate |
| Cached input | 1.00 USD / 1 M tokens | Reading reused prefixes |
| Cache write or storage | 12,50–20,00 USD / 1 M tokens | The condition varies by provider |
| Standard output | 50.00 USD / 1 M tokens | May include reasoning tokens |
| Batch input | 5.00 USD / 1 M tokens | Asynchronous processing |
| Batch output | 25.00 USD / 1 M tokens | Asynchronous processing |
Consult the primary source before budgeting for a deployment.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Terminal-Bench Science 0.1 | 52,6 % | Accuracy | View source ↗ |
| CursorBench 3.2 | 73,4 % | Accuracy | View source ↗ |
| Humanity's Last Exam | 65,0 % | With tools | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Claude Fable 5.1
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
Claude Fable 5.1: technical contract, limits, and testing before assigning high-cost tasks
Claude Fable 5.1 should be evaluated as an execution contract, not as a capability label. This analysis separates what Google Cloud and Amazon Bedrock declare from what depends on the channel and what a team must measure before granting autonomy to a production workflow.
23 Sep 2026 ↗
BrowseComp: what an agent that finds a difficult fact on the web measures, and why getting it right does not prove it conducts reliable research
BrowseComp evaluates whether an agent can locate a brief, hard-to-find factual answer through persistent web browsing. It is a useful signal, but a limited one: a high score is not enough to establish research quality, source traceability, or reliability on open-ended tasks.
22 Sep 2026 ↗
CursorBench 3.2: What a Coding-Agent Benchmark Can Say—and Why It Is Not Enough to Choose a Model Outside Cursor
CursorBench provides a signal about agent systems evaluated within Cursor’s harness, but a score is not a portable property of a model. The verified public documentation reviewed describes CursorBench 3.1, not 3.2; therefore, any reference to an alleged 3.2 version must be treated as unconfirmed until Cursor publishes its methodology and results.
22 Sep 2026 ↗
Claude Fable 5.1: when caching and batch processing reduce cost per task—and when they only shift the bill
The price per million tokens is not enough to choose between a standard call, instruction caching, or batch processing. This guide provides a cost model per correctly completed task for Claude Fable 5.1, including formulas, scenarios, and minimum telemetry. The outcome depends on reusing context before it expires, controlling retries, and accepting—or not—the asynchronous timeline of Batch API.
22 Sep 2026 ↗
Amazon Nova 2 Lite vs. Claude Fable 5.1 for Document Data Extraction: How to Design a Reproducible Comparison
The available documentation describes the capabilities, pricing, and access policies of Amazon Nova 2 Lite and Claude Fable 5.1, but it does not provide an independent test using a shared corpus. This guide defines a protocol for comparing them in structured document extraction and explains which decisions can be made, which asymmetries must be disclosed, and when neither model should automate the workflow without human review.
22 Sep 2026 ↗
Anthropic: how to verify what changes when you use Claude through an API, partner cloud, or product
Adopting Claude is not simply a matter of selecting a model family. The access channel determines which identifier is used, which retirement schedule governs it, which controls each party administers, and which documentation can support a technical decision. This guide offers a method for separating those layers without turning public policies or safety evaluations into guarantees they do not contain.
22 Sep 2026 ↗07 / SOURCES