Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
AI model by Anthropic. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) is a premium-tier model from Anthropic at $50.00/M output tokens. Benchmark scores (e.g. Coding Index 81.6) suggest it targets workloads where correctness matters more than cost — long-running agents, code generation at scale, and complex multi-step reasoning.
Latency. On latency, Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) reports 66 tok/s output speed and 282340ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) costs $15.00 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Current | $10.00 | $50.00 | 66 tok/s |
| GPT-6 Astra (xhigh) | $10.00 | $50.00 | — |
| GPT-6 Astra (Non-reasoning) | $10.00 | $50.00 | — |
| GPT-6 Astra (max) | $10.00 | $50.00 | — |
| GPT-6 Astra (low) | $10.00 | $50.00 | — |
| GPT-6 Astra (high) | $10.00 | $50.00 | — |