Claude Fable 5
Claude Fable 5 is Anthropic's most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. Claude Fable 5 runs long, complex, and asynchronous tasks with fewer check-ins and is available on AI Gateway via anthropic, vertexAnthropic with adaptive thinking and configurable effort.
import { streamText } from 'ai'
const result = streamText({ model: 'anthropic/claude-fable-5', prompt: 'Why is the sky blue?'})Playground
Try out Claude Fable 5 by Anthropic. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Claude Fable 5
Ask Claude Fable 5 anything to try it out.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
Anthropic | 1M | 7.0s | 87tps | $10.00/M | $50.00/M | Read:$1/M Write: $12.5/M | $10/K + input costs | — | +3 | 07/01/2026 | ||
 Google Vertex AI | 1M | 2.1s | 98tps | $10.00/M | $50.00/M | Read:$1/M Write: $12.5/M | $10/K + input costs | — | +3 | 07/01/2026 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Anthropic
| Model |
|---|
| 1M | 1.0s | 109tps | $3.00/M$2.00/M | $15.00/M$10.00/M | Read:$0.3/M$0.2/M Write: $3.75/M$2.5/M | $10/K + input costs | — | +4 |  | 06/29/2026 | |||
| 1M | 0.7s | 104tps | $5.00/MFast $10.00/M | $25.00/MFast $50.00/M | Read:$0.5/M Write: $6.25/M | $10/K + input costs | — | +4 | | 05/28/2026 | |||
| 1M | 0.7s | 100tps | $5.00/MFast $30.00/M | $25.00/MFast $150.00/M | Read:$0.5/M Write: $6.25/M | $10/K + input costs | — | +4 | | 04/16/2026 | |||
| 1M | 0.8s | 73tps | $3.00/M | $15.00/M | Read:$0.3/M Write: $3.75/M | $10/K + input costs | — | +4 | | 02/17/2026 | |||
| 1M | 1.2s | 58tps | $5.00/MFast $30.00/M | $25.00/MFast $150.00/M | Read:$0.5/M Write: $6.25/M | $10/K + input costs | — | +4 | | 02/05/2026 | |||
| 200K | 0.5s | 125tps | $1.00/M | $5.00/M | Read:$0.1/M Write: $1.25/M | $10.00/K + input costs | — | +4 | | 10/15/2025 |
About Claude Fable 5
Claude Fable 5 became available on AI Gateway on July 1, 2026. Access was briefly suspended under US export controls and restored in July 2026 once the controls were lifted; the restored model is the same model, with updated and more robust safety classifiers. Anthropic describes Claude Fable 5 as a Mythos-class model made safe for general availability, with capabilities that exceed any model Anthropic had widely released before. The launch materials report leading results across nearly every benchmark Anthropic tested, spanning software engineering, knowledge work, vision, and scientific research.
Long-horizon agentic work is the design target. Claude Fable 5 handles long-running, complex, and asynchronous tasks where previous models needed more frequent check-ins. At launch, Claude Fable 5 supports the memory tool, code execution, programmatic tool calling, compaction, tool result clearing through context editing, and vision input, plus task budgets in beta. Those are the building blocks for agents that run for hours without losing state.
Adaptive thinking is always on. Claude Fable 5 decides when and how deeply to reason, and thinking: { type: 'disabled' } is not supported. Use the effort parameter to control thinking depth and cost per request. Raw chain of thought is never returned: set thinking.display to summarized for a readable summary, or keep the default omitted.
Safety classifiers ship as part of Claude Fable 5 and can decline certain requests, including occasional false positives on routine tasks such as coding and debugging. A refusal returns stop_reason: "refusal" as a successful response, not an error, and reports which classifier declined. Configure fallback models through the models array in providerOptions.gateway so AI Gateway retries refused requests on the next Claude model in your list, such as Claude Opus 4.8 or Claude Sonnet 5. Fallbacks work on every API format.
Through AI Gateway, Claude Fable 5 is available with the standard unified API, observability, retries, and failover across anthropic, vertexAnthropic. Set the model to anthropic/claude-fable-5 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference, including for Bring Your Own Key requests.
What To Consider When Choosing a Provider
- Configuration: Claude Fable 5 includes safety classifiers that can decline certain requests, and even routine tasks such as coding and debugging can occasionally trigger them. A declined request returns
stop_reason: "refusal"as a successful response rather than an error. Configure fallback models withproviderOptions.gateway.modelsso AI Gateway retries refused requests on the next model in your list, such as Claude Opus 4.8 or Claude Sonnet 5. Fallbacks work on every API format, and AI Gateway observability tracks refusals. - Configuration: Adaptive thinking is the only thinking mode on Claude Fable 5. Use the
effortparameter to control reasoning depth and cost. Premium per-token rates reward routing: send the hardest work to Claude Fable 5 and keep high-volume simple traffic on a cheaper Claude tier. - Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Claude Fable 5
Best For
- Long-Horizon Agentic Work: Long-running, complex, and asynchronous tasks that previously needed more frequent check-ins
- Demanding Reasoning Problems: Hard software engineering, knowledge work, and scientific research where output quality justifies premium compute
- Large-Context Workloads: A context window of 1M tokens and up to 128K tokens output tokens cover big codebases and long agent histories
- Stateful Autonomous Agents: Memory, compaction, code execution, and programmatic tool calling keep multi-hour sessions on track
- Production Agent Infrastructure: Workflows that benefit from AI Gateway routing across anthropic, vertexAnthropic with retries and failover
Consider Alternatives When
- Cost-Sensitive Production Traffic: Claude Sonnet 5 delivers strong agentic performance at a much lower per-token price
- Latency-Critical Interactive Use: A Haiku-tier model is faster and cheaper for well-bounded, high-throughput requests
- Simpler Response Handling: Sonnet-tier models don't include Fable-specific safety classifiers, which keeps refusal handling out of your integration
Conclusion
Claude Fable 5 makes Mythos-class capability generally available with safeguards in place. Use Claude Fable 5 for the hardest reasoning problems and for agent pipelines that run long, complex, and asynchronous tasks with minimal supervision. Route high-volume or latency-sensitive traffic to a cheaper Claude tier and reserve Claude Fable 5 for work that needs the ceiling.