// head_to_head
Claude Fable 5.1 vs Mercury 2
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Mercury 2 is the cheaper of the two; neither can be ranked on quality here.
Mercury 2 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
anthropic
Claude Fable 5.1
- Blended / 1M
- $20.00
- Context
- 1M
- Released
- Sep 1, 2026
- Overall score
- 83.4
inception
Mercury 2
- Blended / 1M
- $0.375
- Context
- 128K
- Released
- Mar 4, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | Claude Fable 5.1 | Mercury 2 |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 83.4 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.6668 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $20.00 | $0.375win |
| Input price / 1M | $10.00 | $0.250win |
| Output price / 1M | $50.00 | $0.750win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.250 | $0.025win |
| Context window | 1Mwin | 128K |
| Max output tokens | 128Kwin | 50K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Claude Fable 5.1 on top, Mercury 2 below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Claude Fable 5.1 | Mercury 2 |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $5,698/mo | $103.80/mo |
| RAG assistant 8K in / 600 out × 100K requests | $7,100/mo | $155.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $6,540/mo | $134.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $13,263/mo | $295.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $25,125/mo | $587.50/mo |
Which should you pick?
You need to fit large documents in one call
Claude Fable 5.1
Wider context window — 1M against 128K.
You are cost-constrained
Mercury 2
Cheaper on blended list price at $0.375 per million tokens.
Claude Fable 5.1 vs Mercury 2 FAQ
Which is better, Claude Fable 5.1 or Mercury 2?
Mercury 2 is the cheaper of the two; neither can be ranked on quality here. Mercury 2 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is Claude Fable 5.1 cheaper than Mercury 2?
Mercury 2 is cheaper. On a 3:1 input:output blend, Claude Fable 5.1 lists at $20.00 per million tokens and Mercury 2 at $0.375 — Mercury 2 is 53× cheaper. Input and output are priced separately — Claude Fable 5.1 charges $10.00 in and $50.00 out, Mercury 2 charges $0.250 and $0.750 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does Claude Fable 5.1 or Mercury 2 have a bigger context window?
Claude Fable 5.1 has the larger context window: 1M for Claude Fable 5.1 against 128K for Mercury 2. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do Claude Fable 5.1 and Mercury 2 support prompt caching?
Both publish a cached-input rate: $0.250 per million for Claude Fable 5.1 and $0.025 for Mercury 2, against full input rates of $10.00 and $0.250. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.