claude-fable-5 vs claude-fable-5.1
Side-by-side comparison of claude-fable-5 and claude-fable-5.1: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. claude-fable-5.1 outperforms claude-fable-5 on 5 of 5 shared benchmarks.
claude-fable-5
Input / 1M
$10.00
Output / 1M
$50.00
Context
1M
Model ID
anthropic/claude-fable-5
claude-fable-5.1
Input / 1M
$10.00
Output / 1M
$50.00
Context
1M
Model ID
anthropic/claude-fable-5.1
Benchmark comparison
Intelligence Indexreasoning
claude-fable-553.2%
claude-fable-5.156.8%
Coding Indexcoding
claude-fable-576.5%
claude-fable-5.181.6%
GPQA Diamondreasoning
claude-fable-592.6%
claude-fable-5.193.7%
Terminal-Bench Hardagentic
claude-fable-562.9%
claude-fable-5.1N/A
τ²-Benchagentic
claude-fable-598.5%
claude-fable-5.1N/A
SciCodecoding
claude-fable-561.0%
claude-fable-5.163.1%
Humanity's Last Examreasoning
claude-fable-555.5%
claude-fable-5.159.1%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| claude-fable-5 | claude-fable-5.1 | |
|---|---|---|
| Input price / 1M | $10.00 | $10.00 |
| Output price / 1M | $50.00 | $50.00 |
| Context window | 1M tokens | 1M tokens |
| Max output | 128K tokens | 128K tokens |
| Vision input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Computer use | Yes | Yes |
| Provider | Anthropic PBC | Anthropic PBC |
Questions people ask
Is claude-fable-5 better than claude-fable-5.1?
claude-fable-5.1 outperforms claude-fable-5 on 5 of 5 shared benchmarks. See the benchmark comparison above for specifics: claude-fable-5 and claude-fable-5.1 have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, claude-fable-5 or claude-fable-5.1?
claude-fable-5 and claude-fable-5.1 have identical combined pricing.
Can I use claude-fable-5 and claude-fable-5.1 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "anthropic/claude-fable-5" and "anthropic/claude-fable-5.1", no other code changes needed.
What are the context windows?
claude-fable-5 supports up to 1M tokens of context. claude-fable-5.1 supports up to 1M tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between claude-fable-5 and claude-fable-5.1 with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.