Claude Fable 5 vs Claude Fable 5.1
Claude Fable 5.1 is one of Anthropic's newest models and Claude Fable 5 an earlier one, so this is also what moving up costs or saves. Claude Fable 5 and Claude Fable 5.1 charge the same per token: $10 per million tokens read and $50 per million written. The bill can still differ, because the same text can be a different number of tokens on each. Below are both price lists, 8 everyday jobs priced on each, and the count for one text.
- For the same tokens
- The same price, $10 in and $50 out
- Cheaper to read
- Neither, both $10
- Cheaper to write
- Neither, both $50
- Scores higher
- Neither, 162 and 165 are within the range of doubt
- Larger window
- The same, 1M tokens each
Price per million tokens, side by side
In US dollars, as each maker prints them. The better figure in each row is green.
| Claude Fable 5Anthropic · earlier model | Claude Fable 5.1Anthropic | |
|---|---|---|
| InputTokens the model reads | $10 | $10 |
| Cached inputRead again from the cache | $1 | $0.25 |
| Cache writePutting text in the cache | $12.50 | $12.50 |
| OutputTokens it writes, thinking included | $50 | $50 |
| Blend 3:13 tokens read for each 1 written | $20 | $20 |
| Batch inputAnswers collected later | $5 | $5 |
| Batch output | $25 | $25 |
| Context windowTokens it holds at once | 1M | 1M |
| Capability scoreEpoch Capabilities Index; GPT-5 is 150 | 162 | 165 |
| Longest answerTokens it writes in 1 reply | 128K | 128K |
What 8 everyday jobs cost a month on each
Each job at its usual number of runs a day, for 30 days, at the standard price. The cheaper of the 2 is green; open any job in the calculator to change it.
| Job | Claude Fable 5 | Claude Fable 5.1 | Difference |
|---|---|---|---|
| A chat question300 in, 500 out, 100 a day | $84.002.8 cents a run | $84.002.8 cents a run | The same |
| A hard question, with thinking300 in, 1,400 out, 100 a day | $2197.3 cents a run | $2197.3 cents a run | The same |
| A long report, summarised60,000 in, 2,000 out, 20 a day | $42070 cents a run | $42070 cents a run | The same |
| A 40-turn agent task2,800,000 in, 40,000 out, 10 a day | $2,196$7.32 a run | $1,629$5.43 a run | 1.3 times |
| A support bot's reply4,000 in, 300 out, 2,000 a day | $2,2203.7 cents a run | $2,1303.6 cents a run | 1 times |
| Sort a message into a category250 in, 5 out, 50,000 a day | $4,1250.27 cents a run | $4,1250.27 cents a run | The same |
| Read an invoice into fields1,500 in, 250 out, 1,000 a day | $8252.8 cents a run | $8252.8 cents a run | The same |
| Review a pull request25,000 in, 4,500 out, 50 a day | $71348 cents a run | $71348 cents a run | The same |
Your own job on both
Start from a job, then set its size, how often it runs and whether the answers can wait. Both bills follow every change.
A short question and a few paragraphs back.
about 230 words
Instructions or documents the model has read before cost far less the second time.
about 380 words
A month of this job
- Claude Fable 5$84.00
2.8 cents a run
- Claude Fable 5.1$84.00
2.8 cents a run
The 2 cost the same for this job, counted in tokens.
This job on every modelWhy the price per token is only the start
Every maker prints 2 main prices: one for the tokens a model reads (input) and one for the tokens it writes (output). On most current models writing costs 3 to 5 times as much as reading, so which model is cheaper can depend on the job. A job that reads a long document and writes a line pays mostly the input price; a chat that writes paragraphs pays mostly the output price. That is why each comparison prices 8 jobs and not one figure.
The same text is not the same number of tokens on every model. Each maker cuts text its own way, and Anthropic says its models from Claude 4.7 on produce about 30 percent more tokens for the same text than earlier ones. A model with the lower price per token can still send the larger bill, so each comparison counts one of our lessons the way both makers count it.
Discounts change the order too. Work that can wait costs half on a batch at the makers that offer one, and text read again from a cache costs a quarter of the input price or less on every current model here. The price table on each comparison shows who offers what.
Thinking is billed as output, and models differ in how much they think and how long they answer. A price list cannot show that. Before you switch, run the same 10 tasks on both models and compare the bills.
Questions
- Which is cheaper, Claude Fable 5 or Claude Fable 5.1?
- Per token, neither: both charge $10 per million tokens read and $50 per million written. The same text can still be a different number of tokens on each, so the bills can differ.
- Which is better, Claude Fable 5 or Claude Fable 5.1?
- They cannot be told apart on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks: Claude Fable 5 scores 162 and Claude Fable 5.1 165, within the range of doubt around each (GPT-5 is 150). So choose on price and on 10 tasks of your own.
- What does a support bot cost a month on Claude Fable 5 and Claude Fable 5.1?
- At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $2,220 a month on Claude Fable 5 and $2,130 on Claude Fable 5.1: Claude Fable 5 costs 1 times as much for this job.
- What does an AI agent task cost on Claude Fable 5 and Claude Fable 5.1?
- One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs $7.32 on Claude Fable 5 and $5.43 on Claude Fable 5.1. At 10 tasks a day that is $2,196 and $1,629 a month.
- Which has the larger context window, Claude Fable 5 or Claude Fable 5.1?
- Neither: both hold 1M tokens at once, about 1,500 pages of English text.
- Does the same text take the same number of tokens on Claude Fable 5 and Claude Fable 5.1?
- Yes, both are counted the same way: our lesson "How AI writes", 1,700 words long, is about 2,100 to 3,600 tokens on each.
- Is it cheaper to move from Claude Fable 5 to Claude Fable 5.1?
- Per token it costs the same: $10 per million tokens read and $50 written on both. The newer model may still use a different number of tokens for the same work.
- Can I pay less on Claude Fable 5 and Claude Fable 5.1 for work that can wait?
- Yes, on both. With a batch, where you collect the answers later instead of at once, Claude Fable 5 costs $5 per million tokens read and $25 written, and Claude Fable 5.1 $5 and $25.
Sources