Model comparison
Claude Fable 5.1 vs Claude Sonnet 5 pricing, explained
Claude Fable 5.1 lists at 5x the rates of Claude Sonnet 5, but cache hits cost $0.25 against $0.20. Why sessions cost 4.4x, and who Anthropic aims Fable 5.1 at.
· Prices as of September 26, 2026
Claude Fable 5.1
Anthropic · Released September 1, 2026
Anthropic's most capable generally available model, aimed at demanding reasoning and long-horizon agentic coding. Anthropic suggests it when Opus-tier results fall short.
Claude Fable 5.1 facts and comparisonsClaude Sonnet 5
Anthropic · Released June 30, 2026
Anthropic's balance of speed and intelligence, and a drop-in upgrade for Claude Sonnet 4.6. Anthropic pitches it as close to Claude Opus 4.8 at a lower price.
Claude Sonnet 5 facts and comparisons
The short answer
Claude Fable 5.1 lists at 5x the rates of Claude Sonnet 5, and the example agentic coding session costs $10.50 on it against $2.40, a 4.4x gap. Sonnet 5 is Anthropic's everyday balance of speed and intelligence, while Fable 5.1 is its most capable generally available model, which Anthropic suggests for work where Opus-tier results fall short.
Choose Claude Fable 5.1 if
- You have tasks where Opus-tier results fall short, which is when Anthropic suggests Fable 5.1.
- Your work is long-horizon agentic coding or multistep research, the strengths Anthropic lists for Fable 5.1.
Choose Claude Sonnet 5 if
- You want most of your coding at $2 input and $10 output per million tokens, a fifth of Fable 5.1's rates.
- You need zero data retention, which Fable 5.1's 30-day retention requirement rules out.
- You rely on the sonnet alias in Claude Code, which resolves to Sonnet 5 on the Anthropic API.
- You send many uncached requests, where the full 5x gap applies.
Side by side
Specs and prices
| Fact | Claude Fable 5.1 | Claude Sonnet 5 |
|---|---|---|
| Maker | Anthropic | Anthropic |
| API model id | claude-fable-5-1 | claude-sonnet-5 |
| Released | September 1, 2026 | June 30, 2026 |
| Status | Current | Current |
| Context window | 1M tokens | 1M tokens |
| Max output | 128K tokens | 128K tokens |
| Open weights | No | No |
| Input, per 1M tokens | $10 | $2 |
| Cache hit, per 1M | $0.25 | $0.20 |
| Cache write, per 1M | $12.50 (5-minute), $20 (1-hour) | $2.50 (5-minute), $4 (1-hour) |
| Output, per 1M tokens | $50 | $10 |
| Runs in | Claude Code, Cursor, OpenCode, OpenRouter, and GitHub Copilot | Claude Code, Cursor, OpenCode, OpenRouter, and GitHub Copilot |
Standard API rates in US dollars, as published by each maker on September 26, 2026. Batch and priority tiers, taxes, and subscription plans are not included. Claude Fable 5.1: The full 1M context window is billed at standard rates. Claude Sonnet 5: The full 1M context window is billed at standard rates. The launch price became the standard price on August 10, 2026, and a planned increase was cancelled.
Cost
What the same work costs
The same token counts, priced at each model’s published rates. Cached tokens are billed at each maker’s cache prices, so the session shows what caching is worth on each model.
Real sessions differ: the two models count the same code as different numbers of tokens, and reasoning settings change how much each one writes. Your own history is the real test.
| Workload | Claude Fable 5.1 | Claude Sonnet 5 |
|---|---|---|
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $10.50 | $2.40 |
| Large one-off review, 150K input with no cache hits, 10K output | $2.00 | $0.40 |
| Output-heavy generation, 30K input, 80K output | $4.30 | $0.86 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $1,155.00 | $264.00 |
| Where the session’s cost goes | ||
| Cache writes | $6.50 | $1.30 |
| Cache reads | $0.50 | $0.40 |
| Uncached input | $1.00 | $0.20 |
| Output | $2.50 | $0.50 |
- caching saves on the session with Claude Fable 5.1 (62%)
- $17.00
- caching saves on the session with Claude Sonnet 5 (56%)
- $3.10
Why the session costs 4.4x, not 5x
Claude Fable 5.1 charges $10 per million input tokens, $50 per million output tokens, and $12.50 and $20 for 5-minute and 1-hour cache writes. Claude Sonnet 5 charges $2 input, $10 output, and $2.50 and $4 for the same writes. Every one of those is a 5x gap, and work without cache hits pays it in full: the large one-off review costs $2.00 against $0.40, and the output-heavy generation $4.30 against $0.86.
The cache hit is the exception. Anthropic bills Fable 5.1 hits at 0.025x the input price, a quarter of the 0.1x Sonnet 5 pays, so a cached million tokens costs $0.25 against $0.20. Reading the session's 2M cached tokens costs $0.50 and $0.40, nearly the same. That pulls the session gap down to 4.4x, $10.50 against $2.40.
The rest of the Fable 5.1 session is dominated by cache writes at $6.50, 62% of the total, and output at $2.50. Of the $8.10 difference per session, $5.20 is cache writes. Over 110 sessions a month the projection is $1,155.00 against $264.00, an $891.00 difference at API rates.
How Anthropic positions Fable 5.1 and Sonnet 5
The two sit two tiers apart, with Claude Opus 5.5 between them on price. Fable 5.1 is Anthropic's most capable generally available model, aimed at demanding reasoning and long-horizon agentic coding. Sonnet 5 is Anthropic's balance of speed and intelligence, pitched as close to Claude Opus 4.8 at a lower price.
Anthropic frames Fable 5.1 as a step up for when Opus-tier results fall short, not as a default. For Sonnet 5 it claims agentic strengths of its own, planning and using tools like browsers and terminals on its own, along with better reasoning, tool use, and coding than Claude Sonnet 4.6. Moving a task from Sonnet 5 straight to Fable 5.1 skips the tier Anthropic recommends as the starting point for most work.
Limits, defaults, and data retention
On paper the limits match. Both accept 1M tokens of context and write up to 128K tokens of output, and Fable 5.1 bills its full window at standard rates. Both use Anthropic's newer tokenizer, so a prompt counts as roughly the same number of tokens on either and the 5x rate gap carries through to real text.
Both default to high effort. Fable 5.1 keeps adaptive thinking always on, with effort from low to max, and Sonnet 5 has adaptive thinking on by default. In Claude Code, the sonnet alias resolves to Sonnet 5 on the Anthropic API, while Fable 5.1 is chosen with /model fable and is not the default on any plan.
Fable 5.1 requires 30-day data retention, so it is not available under zero data retention, and teams with that requirement have their answer. Claude Code, Cursor, OpenRouter, OpenCode, and GitHub Copilot all offer both models.
Prompt caching
How Anthropic bills cached tokens
Anthropic
Claude caches a prompt prefix up to a breakpoint. One top-level cache_control field places the breakpoint automatically and moves it as the conversation grows, or you can mark up to 4 blocks yourself. Claude Code manages caching for you.
A 5-minute cache write costs 1.25x the input price and a 1-hour write costs 2x. A cache hit costs 0.1x input on most models, 0.05x on Claude Opus 5.5, and 0.025x on Claude Fable 5.1 and Claude Mythos 5.1. Every hit restarts the cache lifetime at no charge.
Anthropic's rule of thumb: a 5-minute write pays for itself after one cache read, and a 1-hour write after two.
In Claude Code, the main conversation uses the 1-hour cache on a Claude subscription and the 5-minute cache with an API key. Each model has its own cache, so switching models starts over.
Source: Anthropic: Prompt caching
Your own numbers
See what Claude Fable 5.1 and Claude Sonnet 5 really cost you.
everyaitoken reads your Claude Code, Cursor, OpenCode, and OpenRouter history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.
FAQ
Questions
How much more expensive is Claude Fable 5.1 than Claude Sonnet 5?
5x per token for input, output, and cache writes. Cache hits are $0.25 against $0.20, so the example agentic session is 4.4x: $10.50 against $2.40.
Is there a Claude model between Sonnet 5 and Fable 5.1?
Yes. Claude Opus 5.5 sits between them on price, and Anthropic calls it its recommended starting model for most work. Anthropic suggests Fable 5.1 when Opus-tier results fall short.
Do Claude Fable 5.1 and Claude Sonnet 5 have the same context window?
Yes, 1M tokens each, with up to 128K tokens of output on both.
How can I see what moving work to Fable 5.1 would cost?
Start from what you use now. EveryToken reads your local Claude Code history, prices every request at Anthropic's API rates, and shows cost and cache savings per model, so you can see what share of your spend would move up a tier.
Sources
- Anthropic: Pricing
- Anthropic docs: Claude Fable 5.1
- Anthropic: Claude Fable 5.1 and Claude Mythos 5.1
- Claude Code docs: Model configuration
- Cursor docs: Claude Fable 5.1
- OpenRouter: Claude Fable 5.1
- OpenCode docs: Zen
- GitHub Docs: Supported AI models in Copilot
- Anthropic docs: Claude Sonnet 5
- Anthropic: Introducing Claude Sonnet 5
- Cursor docs: Claude Sonnet 5
- OpenRouter: Claude Sonnet 5
- Anthropic: Prompt caching