Claude Fable 5.1
- Input / 1M tokens
- $10.00
- Output / 1M tokens
- $50.00
- Providers
- 4
- Uptime, 24 h
- 100%
API models · Side by side
Claude Fable 5.1 vs Claude Opus 5.5
Claude Fable 5.1 and Claude Opus 5.5 are Anthropic's two most capable models. The real question is whether Fable is worth paying more for: it costs 2.5 times as much per token, and Anthropic's own advice is to start with Opus.
Claude Opus 5.5
- Input / 1M tokens
- $4.00
- Output / 1M tokens
- $20.00
- Providers
- 5
- Uptime, 24 h
- 100%
The short answer
Opus 5.5 charges $4 per million input tokens and $20 per million output tokens; Fable 5.1 charges $10 and $50. Both read up to 1 million tokens, write up to 128,000 per reply and accept text, images and files. Anthropic lists Fable as slower and recommends it for demanding reasoning and long-running agent work, or when Opus at higher effort still doesn't pass your tests.
Estimate your monthly bill
Enter your own usage. We apply each model's current rates, including long-prompt pricing, for a 30-day month.
Try:
Claude Fable 5.1$1,350.00per month
Claude Opus 5.5$540.00per month
A token is roughly three-quarters of an English word. Cached input, reasoning tokens, tools and media are not included.
Compare the details
Compare context, supported inputs and usage costs. Highlighted rows show a difference.
| Feature | Claude Fable 5.1 | Claude Opus 5.5 |
|---|---|---|
| Input formats | file, image, text | file, image, text |
| Output formats | text | text |
| Context / position limit | 1,000,000 | 1,000,000 |
| Endpoint output limit (tokens) | 128,000 | 128,000 |
| Developer features | Reasoning output, Completion limit, Output limit, Reasoning controls, Thinking effort, Response format, Stop sequences, Structured output, Tool selection, Tool calling, Response length | Reasoning output, Completion limit, Output limit, Reasoning controls, Thinking effort, Response format, Stop sequences, Structured output, Tool selection, Tool calling, Response length |
| Cached input / 1M tokens | $0.25 | $0.20 |
| Cache write / 1M tokens | $12.50 | $5.00 |
| USD input / 1M tokens | $10.00 | $4.00 |
| USD output / 1M tokens | $50.00 | $20.00 |
| Available API providers | 4 | 5 |
| Best provider uptime, last 24 h | 100% | 100% |
| Model identifier | anthropic/claude-fable-5.1 | anthropic/claude-opus-5.5 |
API pricing
Prices are in USD per million tokens. Input is what you send; output is what the model generates. Chat subscriptions and API usage are billed separately.
Tools, images and additional reasoning can add charges. The examples below cover input and output tokens only.
Compare local modelsWhat those prices mean in practice
Each example uses the same token budget for both models. These are calculations, not measured workloads. Cache discounts, media, tools and extra reasoning are excluded.
| Workload | Claude Fable 5.1 | Claude Opus 5.5 |
|---|---|---|
| 1,000 short requestsPer request: 2,000 input + 500 output tokens | $45.00 | $18.00 |
| 100 document summariesPer request: 20,000 input + 1,000 output tokens | $25.00 | $10.00 |
| 10 long-document requestsPer request: 300,000 input + 2,000 output tokens | $31.00 | $12.40 |
Estimate = requests × (input tokens × input price + output tokens × output price) ÷ 1,000,000. Long-prompt rates are applied where the pricing data provides them. Real requests can use different amounts of output.
Beyond the price tag
What 2.5× costs in practice
Neither model charges extra for long prompts, so Fable costs 2.5 times as much at every request size. At 1,000 short requests a day (2,000 tokens in, 500 out), that is about $1,350 a month on Fable against $540 on Opus. If results can wait, the Batch API halves both: $2 and $10 per million for Opus, $5 and $25 for Fable.
Caching narrows the gap
Fable's cache reads cost $0.25 per million tokens, only a little more than Opus's $0.20. That matters for agents that send the same large context at every step. Take a run that caches a 200,000-token context once, then re-reads it on 50 steps and writes 2,000 tokens each time: about $5 on Opus and $10 on Fable, ignoring the small uncached part of each prompt. Writing to the cache still costs 2.5× more on Fable ($12.50 against $5 per million for 5-minute caching).
Speed and thinking
Anthropic rates Opus 5.5 as moderate and Fable 5.1 as slower. Both always think before answering, and thinking tokens are billed as output. Fable defaults to high effort and Opus to medium, so set the same effort level when you compare them, or you are testing the setting as well as the model. Opus 5.5 also offers fast mode, on the Claude API and Anthropic-managed Google Cloud, at $8 and $40 per million tokens; Fable doesn't.
API differences to plan for
Fable 5.1 returns an error if you force a specific tool call, and only Fable 5.1 and its restricted sibling Mythos 5.1 can read its thinking blocks, which matters if you hand a conversation from one model to another. On the Batch API, Opus 5.5 can write up to 300,000 output tokens per request with a beta header; Fable stays at 128,000.
Which one should you pick?
Start with Opus 5.5: it takes the same inputs and context at 40% of Fable's price. Move a task to Fable 5.1 when Opus at high effort still fails your tests, such as long agent runs that stall, multi-step research or hard reasoning where a wrong answer is expensive. Send only those tasks to Fable rather than switching everything.
Common questions
Is Claude Fable 5.1 better than Opus 5.5?
Anthropic positions Fable 5.1 for demanding reasoning and long-running agent work, and recommends Opus 5.5 for most workloads. Whether Fable is better for you depends on your tasks, so test both at the same effort level on real examples.
How much more does Fable cost than Opus?
2.5 times more per input and output token: $10 and $50 per million against $4 and $20. Cache reads are closer, at $0.25 against $0.20 per million.
What is Claude Mythos 5.1?
It has the same capabilities and prices as Fable 5.1, but Anthropic only offers it to organizations verified through its programs, such as the Cyber Verification Program.
Are these Claude subscription prices?
No. They're pay-per-use API prices. The Claude apps have their own monthly plans and usage limits.
Where can I use them?
Both are available on the Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry and Claude Platform on AWS. Choosing US-only processing on the Claude API adds 10% to every token price on both models.