Technical Specifications of Claude Fable 5.1
| Specification | Claude Fable 5.1 |
|---|---|
| Provider | Anthropic |
| Model ID | claude-fable-5-1 |
| Model family | Claude Fable 5.1 / Mythos-class |
| Release date | September 1, 2026 |
| Context window | 1,000,000 tokens |
| Maximum output | 128,000 tokens |
| Input | Text, images |
| Output | Text |
| Thinking | Adaptive thinking, always on |
| Default effort | high |
| Effort levels | low, medium, high, xhigh, max |
| Knowledge cutoff | June 2026 |
| API platforms | Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry |
| Comparative latency | Slower |
| Status | Active |
Anthropic positions Claude Fable 5.1 specifically for demanding reasoning and long-horizon agentic work. Its 1M-token context and 128K maximum output make it suitable for large repositories, lengthy research material, and extended multi-step workflows.
What Is Claude Fable 5.1?
Claude Fable 5.1 is Anthropic's September 2026 upgrade to the Fable 5 model, targeting complex reasoning, long-running agentic coding, multi-step research, and professional knowledge work.
Rather than simply increasing the model's general-purpose intelligence, Fable 5.1 focuses heavily on task completion over long horizons. Anthropic specifically highlights improvements in agentic coding, research, and document, spreadsheet, and presentation workflows.
Fable 5.1 belongs to Anthropic's Mythos-class tier. Claude Mythos 5.1 shares the same underlying capabilities but is restricted to Project Glasswing participants, while Fable 5.1 is the generally available safeguarded version.
Main Features of Claude Fable 5.1
- 1M-token long context: The model can maintain extremely large amounts of source material, repository context, conversation history, or research evidence within a single context window.
- Long-horizon agentic execution: Fable 5.1 is optimized for tasks requiring many sequential actions rather than isolated question-answering, including extended coding and research workflows.
- Adaptive thinking: Thinking is always enabled, while the
effortsetting controls the amount of reasoning allocated to a request. Available levels arelow,medium,high,xhigh, andmax. - Strong software engineering: Anthropic reports improvements on agentic coding evaluations, including Terminal-Bench 4.0, CursorBench, and AutomationBench.
- Multimodal document understanding: Fable 5.1 accepts text and image inputs, making it suitable for documents, screenshots, diagrams, spreadsheets, and other visual material.
- Lower cache-read cost: Prompt-cache reads are priced at $0.25 per million tokens, 75% below Fable 5's $1 per million cached tokens. Anthropic estimates this can reduce typical workload costs by about 25% and highly agentic workloads by up to approximately 45%.
Benchmark Performance of Claude Fable 5.1
Anthropic's September 1 evaluation compares Fable 5.1 with Fable 5, Claude Opus 5, and GPT-5.6 Sol. The strongest gains appear on long-running agentic tasks rather than conventional knowledge benchmarks.
| Benchmark | Fable 5.1 | Fable 5 | Opus 5 | GPT-5.6 Sol |
|---|---|---|---|---|
| Terminal-Bench-Science 0.1 | 52.6% | 24.7% | 29.0% | 22.4% |
| Terminal-Bench 4.0 | 55.8% | 42.0% | 52.3% | 37.3% |
| AutomationBench | 31.4% | 17.1% | 26.9% | 19.6% |
| CursorBench 3.2.0 | 73.4% | 70.5% | 70.0% | 67.2% |
| OSWorld 2.0 — partial | 77.9% | 72.9% | 75.4% | — |
| OSWorld 2.0 — strict | 41.7% | 36.1% | 39.6% | — |
| Humanity's Last Exam — no tools | 60.9% | 57.8% | 56.6% | — |
| Humanity's Last Exam — with tools | 65.0% | 63.8% | 63.6% | — |
| GDPval-AA v2 | 1,853 Elo | 1,723 | 1,824 | 1,711 |
The largest improvement is on Terminal-Bench-Science 0.1, where Fable 5.1 reaches 52.6%, compared with 24.7% for Fable 5. On GDPval-AA v2, Fable 5.1 reaches 1,853 Elo, ahead of Opus 5 at 1,824 and Fable 5 at 1,723.
Artificial Analysis independently reports that Fable 5.1 reaches a 66 Intelligence Index score at maximum effort, placing it ahead of Opus 5 at 63 and Fable 5 at 60 in that evaluation.
Benchmark results should nevertheless be interpreted by workload. For example, third-party benchmark aggregation reports Fable 5.1 at 89.1% on SWE-bench Multilingual versus 89.5% for Opus 5, illustrating that Fable 5.1 does not automatically dominate every specialized evaluation.
Claude Fable 5.1 vs Claude Fable 5 vs Claude Opus 5
| Model | Context | Max Output | Primary Position | Default Effort |
|---|---|---|---|---|
| Claude Fable 5.1 | 1M | 128K | Long-horizon reasoning and agentic work | High |
| Claude Fable 5 | 1M+ | 128K | Previous Fable generation | High |
| Claude Opus 5 | 1M | 128K | Complex agentic coding and enterprise work | High |
Fable 5.1 is the stronger choice when the workload involves long-running autonomous execution, demanding reasoning, multi-step research, or complex coding. Anthropic itself recommends starting most workloads with Opus 5 and moving to Fable 5.1 when higher-effort Opus 5 evaluations remain insufficient.
Compared with Fable 5, the major changes are improved agentic performance, lower cache-read costs, per-message effort controls, progress updates, and changes to thinking-block and tool-use behavior.
Limitations of Claude Fable 5.1
Fable 5.1 is not the fastest or cheapest Claude model. Anthropic classifies its comparative latency as slower, and its standard input/output rates are higher than Opus 5 and Sonnet 5.
It also has important API migration differences from Fable 5. In particular, forced tool use with tool_choice: any or tool returns a 400 error, while auto and none remain supported. Applications migrating from Fable 5 should also account for changes involving thinking blocks and conversation history.
Fable 5.1 also operates with production safety classifiers. Some restricted cybersecurity and biology requests can trigger refusal or fallback behavior, so benchmark results on tasks affected by safeguards should not be interpreted as unrestricted Mythos-class capability.
Best Use Cases for Claude Fable 5.1
- Repository-scale software engineering — multi-file refactoring, debugging, migration, testing, and long-running coding agents.
- Autonomous research — multi-step investigation requiring search, evidence collection, analysis, and synthesis.
- Large-document analysis — processing extensive technical documentation, contracts, reports, or research collections.
- Computer-use workflows — tasks involving desktop interfaces, spreadsheets, presentations, and other visual environments.
- Enterprise knowledge work — complex reports, financial or analytical workflows, and professional deliverables requiring sustained reasoning.
- Agentic systems — applications where the model must repeatedly call tools, inspect results, revise its plan, and continue until a task is complete.Technical Specifications of Claude Fable 5.1
| Specification | Claude Fable 5.1 |
|---|---|
| Provider | Anthropic |
| Model ID | claude-fable-5-1 |
| Model family | Claude Fable 5.1 / Mythos-class |
| Release date | September 1, 2026 |
| Context window | 1,000,000 tokens |
| Maximum output | 128,000 tokens |
| Input | Text, images |
| Output | Text |
| Thinking | Adaptive thinking, always on |
| Default effort | high |
| Effort levels | low, medium, high, xhigh, max |
| Knowledge cutoff | June 2026 |
| API platforms | Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry |
| Comparative latency | Slower |
| Status | Active |
Anthropic positions Claude Fable 5.1 specifically for demanding reasoning and long-horizon agentic work. Its 1M-token context and 128K maximum output make it suitable for large repositories, lengthy research material, and extended multi-step workflows.
What Is Claude Fable 5.1?
Claude Fable 5.1 is Anthropic's September 2026 upgrade to the Fable 5 model, targeting complex reasoning, long-running agentic coding, multi-step research, and professional knowledge work.
Rather than simply increasing the model's general-purpose intelligence, Fable 5.1 focuses heavily on task completion over long horizons. Anthropic specifically highlights improvements in agentic coding, research, and document, spreadsheet, and presentation workflows.
Fable 5.1 belongs to Anthropic's Mythos-class tier. Claude Mythos 5.1 shares the same underlying capabilities but is restricted to Project Glasswing participants, while Fable 5.1 is the generally available safeguarded version.
Main Features of Claude Fable 5.1
- 1M-token long context: The model can maintain extremely large amounts of source material, repository context, conversation history, or research evidence within a single context window.
- Long-horizon agentic execution: Fable 5.1 is optimized for tasks requiring many sequential actions rather than isolated question-answering, including extended coding and research workflows.
- Adaptive thinking: Thinking is always enabled, while the
effortsetting controls the amount of reasoning allocated to a request. Available levels arelow,medium,high,xhigh, andmax. - Strong software engineering: Anthropic reports improvements on agentic coding evaluations, including Terminal-Bench 4.0, CursorBench, and AutomationBench.
- Multimodal document understanding: Fable 5.1 accepts text and image inputs, making it suitable for documents, screenshots, diagrams, spreadsheets, and other visual material.
- Lower cache-read cost: Prompt-cache reads are priced at $0.25 per million tokens, 75% below Fable 5's $1 per million cached tokens. Anthropic estimates this can reduce typical workload costs by about 25% and highly agentic workloads by up to approximately 45%.
Benchmark Performance of Claude Fable 5.1
Anthropic's September 1 evaluation compares Fable 5.1 with Fable 5, Claude Opus 5, and GPT-5.6 Sol. The strongest gains appear on long-running agentic tasks rather than conventional knowledge benchmarks.
| Benchmark | Fable 5.1 | Fable 5 | Opus 5 | GPT-5.6 Sol |
|---|---|---|---|---|
| Terminal-Bench-Science 0.1 | 52.6% | 24.7% | 29.0% | 22.4% |
| Terminal-Bench 4.0 | 55.8% | 42.0% | 52.3% | 37.3% |
| AutomationBench | 31.4% | 17.1% | 26.9% | 19.6% |
| CursorBench 3.2.0 | 73.4% | 70.5% | 70.0% | 67.2% |
| OSWorld 2.0 — partial | 77.9% | 72.9% | 75.4% | — |
| OSWorld 2.0 — strict | 41.7% | 36.1% | 39.6% | — |
| Humanity's Last Exam — no tools | 60.9% | 57.8% | 56.6% | — |
| Humanity's Last Exam — with tools | 65.0% | 63.8% | 63.6% | — |
| GDPval-AA v2 | 1,853 Elo | 1,723 | 1,824 | 1,711 |
The largest improvement is on Terminal-Bench-Science 0.1, where Fable 5.1 reaches 52.6%, compared with 24.7% for Fable 5. On GDPval-AA v2, Fable 5.1 reaches 1,853 Elo, ahead of Opus 5 at 1,824 and Fable 5 at 1,723.
Artificial Analysis independently reports that Fable 5.1 reaches a 66 Intelligence Index score at maximum effort, placing it ahead of Opus 5 at 63 and Fable 5 at 60 in that evaluation.
Benchmark results should nevertheless be interpreted by workload. For example, third-party benchmark aggregation reports Fable 5.1 at 89.1% on SWE-bench Multilingual versus 89.5% for Opus 5, illustrating that Fable 5.1 does not automatically dominate every specialized evaluation.
Claude Fable 5.1 vs Claude Fable 5 vs Claude Opus 5
| Model | Context | Max Output | Primary Position | Default Effort |
|---|---|---|---|---|
| Claude Fable 5.1 | 1M | 128K | Long-horizon reasoning and agentic work | High |
| Claude Fable 5 | 1M+ | 128K | Previous Fable generation | High |
| Claude Opus 5 | 1M | 128K | Complex agentic coding and enterprise work | High |
Fable 5.1 is the stronger choice when the workload involves long-running autonomous execution, demanding reasoning, multi-step research, or complex coding. Anthropic itself recommends starting most workloads with Opus 5 and moving to Fable 5.1 when higher-effort Opus 5 evaluations remain insufficient.
Compared with Fable 5, the major changes are improved agentic performance, lower cache-read costs, per-message effort controls, progress updates, and changes to thinking-block and tool-use behavior.
Limitations of Claude Fable 5.1
Fable 5.1 is not the fastest or cheapest Claude model. Anthropic classifies its comparative latency as slower, and its standard input/output rates are higher than Opus 5 and Sonnet 5.
It also has important API migration differences from Fable 5. In particular, forced tool use with tool_choice: any or tool returns a 400 error, while auto and none remain supported. Applications migrating from Fable 5 should also account for changes involving thinking blocks and conversation history.
Fable 5.1 also operates with production safety classifiers. Some restricted cybersecurity and biology requests can trigger refusal or fallback behavior, so benchmark results on tasks affected by safeguards should not be interpreted as unrestricted Mythos-class capability.
Best Use Cases for Claude Fable 5.1
- Repository-scale software engineering — multi-file refactoring, debugging, migration, testing, and long-running coding agents.
- Autonomous research — multi-step investigation requiring search, evidence collection, analysis, and synthesis.
- Large-document analysis — processing extensive technical documentation, contracts, reports, or research collections.
- Computer-use workflows — tasks involving desktop interfaces, spreadsheets, presentations, and other visual environments.
- Enterprise knowledge work — complex reports, financial or analytical workflows, and professional deliverables requiring sustained reasoning.
- Agentic systems — applications where the model must repeatedly call tools, inspect results, revise its plan, and continue until a task is complete.
- How Does CometAPI Access the Claude Fable 5.1 API?
CometAPI provides Claude Fable 5.1 through its unified API gateway, allowing developers to use the model with a CometAPI API key rather than building a separate provider integration. CometAPI currently lists Claude Fable 5.1 (claude-fable-5-1) as live, with an Anthropic-compatible /v1/messages endpoint and an OpenAI-compatible /v1/chat/completions endpoint.
Step 1: Create a CometAPI Account and Get an API Key
Create or sign in to your CometAPI account and generate a CometAPI API key from the dashboard. The same key can be used across the models available through CometAPI, so you do not need to create a separate credential specifically for Claude Fable 5.1.
Step 2: Select Claude Fable 5.1 and Configure the API
Choose Claude Fable 5.1 from the CometAPI model catalog and use the model ID claude-fable-5-1. Set CometAPI as the API endpoint and select the API format appropriate for your application: CometAPI provides both an Anthropic-compatible Messages endpoint and an OpenAI-compatible Chat Completions endpoint for the model.
This means applications already built around common LLM SDK patterns can switch to Claude Fable 5.1 without redesigning their entire application architecture.
Step 3: Send Requests and Process the Response
Send your prompt to Claude Fable 5.1 through CometAPI and process the returned response in your application. You can use the model for demanding reasoning, long-running coding agents, multi-step research, document analysis, and other complex workflows.
Because Fable 5.1 supports a 1M-token context window, 128K maximum output, and adaptive thinking, developers can send substantially larger contexts and allow the model to work through more complex tasks than a conventional short-turn chatbot workflow.
Why Should You Choose CometAPI for Claude Fable 5.1?
One API for Claude and Other Frontier Models
The biggest advantage is not merely access to Claude Fable 5.1. CometAPI provides a single API layer across 500+ AI models, allowing developers to evaluate Fable 5.1 alongside other Claude, OpenAI, Google, xAI, DeepSeek, and other models without maintaining separate provider integrations.
This is particularly useful when building an AI application that needs different models for different workload tiers—for example, Fable 5.1 for difficult agentic tasks and less expensive models for routine requests.
Lower Listed CometAPI Pricing
CometAPI currently lists Claude Fable 5.1 with a 20% discount, showing $8 per 1M tokens on its model catalog compared with the listed $10 per 1M-token input price from Anthropic.
For applications processing large volumes of tokens, this difference can materially affect operating costs. Developers should still check the live CometAPI model page for the applicable input/output pricing and billing rules before production deployment.
Easier Model Switching
Using an aggregation layer makes it easier to compare Claude Fable 5.1 with alternatives without rebuilding the application around a different provider.
For example, a team can evaluate:
Fable 5.1 → Opus 5 → Sonnet 5 → another frontier model
against the same prompts, application logic, and evaluation set. This is especially valuable because Anthropic itself recommends Opus 5 for most workloads, while positioning Fable 5.1 for demanding reasoning and long-horizon agentic work.
Unified Billing and API Management
Instead of managing separate API credentials, billing arrangements, and integrations for every model provider, CometAPI provides a centralized interface for model access and usage.
That makes CometAPI particularly useful for teams experimenting with multiple frontier models or building applications where the optimal model may change as pricing, availability, or performance changes.
Better Fit for Agentic Workflows
Claude Fable 5.1 is specifically designed for long-running agentic work. CometAPI's multi-model environment lets developers place Fable 5.1 inside a broader routing or fallback strategy rather than making the application dependent on a single model.
For example, a production workflow can reserve Fable 5.1 for high-complexity coding, deep research, and long-horizon tasks, while routing simpler or high-volume requests to more economical models.
In short: choose CometAPI when you want Claude Fable 5.1 without locking your application into a single AI provider—and when centralized model access, discounted pricing, easier model comparison, and the ability to switch between frontier models are more valuable than maintaining separate integrations for each provider.