Speed analysis
Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.
Pricing
What you pay per million tokens when you use this model on Tokonomix, plus an estimate for a typical conversation.
Tokens per second
Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.
Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.
Capabilities
Availability
Availability
How often this model answers when we call it — measured across real API requests and live tests over the last 30 days. This is separate from quality: these numbers only tell you whether the model responds, not how good the answer is.
Last 7 days
—
Last 30 days
100.0%
n=36
Median response time
22,427ms
n=36
Based on 393 measurements over the last 30 days.
Technical details
Only live API calls and live-test requests count — internal probes and benchmark runs are excluded.
Calls with a custom API key (BYOK) are excluded: those failures are key-specific, not a sign of model downtime.
Failed calls are NOT included in quality scores — quality is measured on successful responses only. Availability and quality are independent signals.
Median response time (p50) across successful calls with a recorded duration. Outliers (very slow or very fast calls) pull the median less than the average.
Total calls (30d)
36
OK responses (30d)
36
Total calls (7d)
0
OK responses (7d)
0
Tokonomix benchmark verdicts
Claude Fable 5.1 gains seven new capabilities with no benchmark data yet
Claude Fable 5.1 has expanded significantly with seven new capabilities added since the previous benchmark window: tools, vision, json_mode, pdf_input, reasoning, json_schema, and prompt_caching. This represents a substantial feature expansion that positions the model for more diverse use cases including multimodal applications, structured output generation, and enhanced document processing. However, no benchmark performance data is available for either the current or previous window, making it impossible to assess actual performance quality, accuracy, or reliability across standard evaluation metrics. The addition of reasoning capabilities and tool use suggests potential for agentic workflows, while vision and PDF input support indicates broader content processing abilities. Prompt caching could offer efficiency improvements for repetitive tasks. Without concrete benchmark results, users should approach deployment cautiously and conduct their own testing for specific use cases. The model's practical performance, latency characteristics, and quality compared to alternatives remains unvalidated by independent measurements. Organizations considering adoption should wait for benchmark data or perform thorough internal evaluation before production deployment.
Quality
—
Latency p50
—
Test runs
0
Claude Fable 5.1
by Anthropic
- Context window
- 1M tokens
- Input price
- $13.00 / 1M
- Output price
- $65.00 / 1M
- Tier
- Tier A — Frontier
- Modality
- Text + vision
- API type
- REST · streaming
- Benchmark runs
- 213
More from Anthropic