Model vs model
Claude Fable 5.1 vs Claude Sonnet 5
Claude Fable 5.1 and Claude Sonnet 5 are both in llmwise. What each gets on every plan, what it reads, how it's served and what happens when its provider fails, from the catalog and the code that runs them.
Model prices and specs checked against OpenRouter's Claude Fable 5.1 page, OpenRouter's Claude Sonnet 5 page. Updated .
Short answer
Claude Sonnet 5 gets four times as many messages: up to 125 messages a month on Pro, against up to 31 messages a month for Claude Fable 5.1. Otherwise, only Claude Fable 5.1 can be passed to another model by its maker's safety system and only Claude Sonnet 5 is in the free trial. In our test runs, Claude Fable 5.1 passed 45 of the 50 prompts both answered and Claude Sonnet 5 46; 5 prompts split them, most on writing (3 to 4).
Claude Fable 5.1 vs Claude Sonnet 5, prompt by prompt
Every prompt Claude Fable 5.1 and Claude Sonnet 5 both answered, compared directly, their biggest differences first. One run each, through OpenRouter: a wait depends on the provider and the load that day, so a lead under 10% counts as close.
Of the 50 prompts both answered, both passed 43, only Claude Fable 5.1 passed 2, only Claude Sonnet 5 passed 3, and neither passed 2. Claude Fable 5.1 answered sooner on 5 of the 50 and Claude Sonnet 5 on 39; the rest were within 10% of each other. The 50 replies cost $1.0018 on Claude Fable 5.1 and $0.2030 on Claude Sonnet 5: 4.9× less on Claude Sonnet 5.
The 5 prompts only one of Claude Fable 5.1 and Claude Sonnet 5 passed
Announce a second bakery shop on LinkedIn (writing): Claude Fable 5.1 passed and Claude Sonnet 5 didn't. Claude Fable 5.1: Graded 4.8 of 5 on average (lowest 4). Claude Sonnet 5: Graded 3.5 of 5 on average (lowest 3).
A product announcement with five rules (writing): Claude Sonnet 5 passed and Claude Fable 5.1 didn't. Claude Fable 5.1: Graded 3.7 of 5 on average (lowest 3). Claude Sonnet 5: Graded 4.3 of 5 on average (lowest 4).
Argue both sides of free buses (writing): Claude Sonnet 5 passed and Claude Fable 5.1 didn't. Claude Fable 5.1: Graded 4.7 of 5 on average (lowest 4); but a paragraph of 99 words, over the 90 allowed. Claude Sonnet 5: Graded 4.0 of 5 on average (lowest 4).
Correlation between ad spend and sign-ups (data analysis): Claude Fable 5.1 passed and Claude Sonnet 5 didn't. Claude Fable 5.1: Final answer 0.97: right. Claude Sonnet 5: Final answer 0.99; expected 0.97.
A message with a planted instruction (customer support): Claude Sonnet 5 passed and Claude Fable 5.1 didn't. Claude Fable 5.1: Graded 4.7 of 5 on average (lowest 4); but 159 words, over the 150 allowed. Claude Sonnet 5: Graded 4.0 of 5 on average (lowest 3).
Job by job, the widest gaps first
Customer support: Claude Fable 5.1 passed 4 of 5 and Claude Sonnet 5 5 of 5. Claude Sonnet 5 answered 1.7× sooner at the median, 6.1 s against 3.5 s. Claude Sonnet 5 cost 6.1× less, $0.1103 against $0.0182 for the 5 replies. Their replies ran to about the same length.
Writing: Claude Fable 5.1 passed 3 of 5 and Claude Sonnet 5 4 of 5. Claude Sonnet 5 answered 1.3× sooner at the median, 6.0 s against 4.5 s. Claude Sonnet 5 cost 5.1× less, $0.0862 against $0.0171 for the 5 replies. Their replies ran to about the same length.
Data analysis: Claude Fable 5.1 passed 5 of 5 and Claude Sonnet 5 4 of 5. Their median waits were close, 4.9 s against 5.3 s. Claude Sonnet 5 cost 4.1× less, $0.1415 against $0.0344 for the 5 replies. Claude Fable 5.1's replies ran 23% longer, in tokens of reply, thinking not counted.
RAG and answering from documents: Claude Fable 5.1 passed 5 of 5 and Claude Sonnet 5 5 of 5. Claude Sonnet 5 answered 2.2× sooner at the median, 4.0 s against 1.8 s. Claude Sonnet 5 cost 6.7× less, $0.0727 against $0.0109 for the 5 replies. Claude Fable 5.1's replies ran 81% longer, in tokens of reply, thinking not counted.
SQL: Claude Fable 5.1 passed 5 of 5 and Claude Sonnet 5 5 of 5. Claude Sonnet 5 answered 2.1× sooner at the median, 4.5 s against 2.2 s. Claude Sonnet 5 cost 6.5× less, $0.0924 against $0.0142 for the 5 replies. Claude Fable 5.1's replies ran 38% longer, in tokens of reply, thinking not counted.
Translation: Claude Fable 5.1 passed 5 of 5 and Claude Sonnet 5 5 of 5. Claude Sonnet 5 answered 1.9× sooner at the median, 5.1 s against 2.8 s. Claude Sonnet 5 cost 5.9× less, $0.0877 against $0.0149 for the 5 replies. Claude Fable 5.1's replies ran 14% longer, in tokens of reply, thinking not counted.
Summarization: Claude Fable 5.1 passed 3 of 5 and Claude Sonnet 5 3 of 5. Claude Sonnet 5 answered 1.8× sooner at the median, 5.0 s against 2.7 s. Claude Sonnet 5 cost 5.8× less, $0.0805 against $0.0140 for the 5 replies. Their replies ran to about the same length.
Agents and tool use: Claude Fable 5.1 passed 5 of 5 and Claude Sonnet 5 5 of 5. Claude Sonnet 5 answered 1.8× sooner at the median, 3.5 s against 2.0 s. Claude Sonnet 5 cost 4.9× less, $0.0598 against $0.0121 for the 5 replies. Claude Fable 5.1's replies ran 13% longer, in tokens of reply, thinking not counted.
Coding: Claude Fable 5.1 passed 5 of 5 and Claude Sonnet 5 5 of 5. Claude Sonnet 5 answered 2.1× sooner at the median, 5.5 s against 2.7 s. Claude Sonnet 5 cost 4.2× less, $0.2126 against $0.0508 for the 5 replies. Claude Fable 5.1's replies ran 32% longer, in tokens of reply, thinking not counted.
Math: Claude Fable 5.1 passed 5 of 5 and Claude Sonnet 5 5 of 5. Claude Sonnet 5 answered 1.2× sooner at the median, 4.6 s against 3.9 s. Claude Sonnet 5 cost 3.5× less, $0.0582 against $0.0165 for the 5 replies. Their replies ran to about the same length.
All 50 prompts: who passed, who answered sooner, who cost less
| Prompt | Result | Sooner | Cheaper |
|---|---|---|---|
| Turn a title into a URL slug | Both passed | Claude Sonnet 5, 2.4×took 5.5 s and 2.3 s | Claude Sonnet 5, 6.9×cost $0.0167 and $0.0024 |
| Parse a duration like “1h 30m” | Both passed | Claude Sonnet 5, 1.8×took 4.7 s and 2.6 s | Claude Sonnet 5, 4.8×cost $0.0173 and $0.0036 |
| Merge overlapping intervals | Both passed | Claude Sonnet 5, 2.0×took 5.3 s and 2.7 s | Claude Sonnet 5, 6.3×cost $0.0214 and $0.0034 |
| Evaluate an arithmetic expression, no eval | Both passed | Closetook 15.7 s and 16.9 s | Claude Sonnet 5, 3.9×cost $0.0874 and $0.0226 |
| Parse CSV with quoted fields | Both passed | Claude Fable 5.1, 1.1×took 14.3 s and 15.8 s | Claude Sonnet 5, 3.7×cost $0.0697 and $0.0187 |
| Announce a second bakery shop on LinkedIn | Only Claude Fable 5.1 | Claude Sonnet 5, 1.6×took 7.3 s and 4.6 s | Claude Sonnet 5, 4.9×cost $0.0184 and $0.0037 |
| Rewrite corporate jargon in plain words | Both passed | Claude Sonnet 5, 2.2×took 6.0 s and 2.7 s | Claude Sonnet 5, 5.8×cost $0.0130 and $0.0022 |
| Decline a meeting and offer two times | Both passed | Claude Sonnet 5, 1.7×took 4.7 s and 2.8 s | Claude Sonnet 5, 5.6×cost $0.0145 and $0.0026 |
| A product announcement with five rules | Only Claude Sonnet 5 | Claude Sonnet 5, 1.3×took 5.9 s and 4.5 s | Claude Sonnet 5, 4.5×cost $0.0157 and $0.0035 |
| Argue both sides of free buses | Only Claude Sonnet 5 | Claude Sonnet 5, 1.4×took 9.3 s and 6.6 s | Claude Sonnet 5, 4.9×cost $0.0246 and $0.0050 |
| A discount, then sales tax | Both passed | Claude Sonnet 5, 1.9×took 3.6 s and 1.9 s | Claude Sonnet 5, 5.6×cost $0.0086 and $0.0015 |
| Pens at 3 for $4 | Both passed | Claude Fable 5.1, 1.2×took 5.4 s and 6.3 s | Claude Sonnet 5, 2.6×cost $0.0159 and $0.0061 |
| Compound interest over three years | Both passed | Closetook 3.6 s and 3.7 s | Claude Sonnet 5, 4.4×cost $0.0092 and $0.0021 |
| Four-digit numbers whose digits sum to 9 | Both passed | Closetook 4.6 s and 4.5 s | Claude Sonnet 5, 3.5×cost $0.0139 and $0.0039 |
| The highest of three dice is a 5 | Both passed | Claude Sonnet 5, 1.5×took 5.9 s and 3.9 s | Claude Sonnet 5, 3.8×cost $0.0106 and $0.0028 |
| An article in three bullets | Neither passed | Claude Sonnet 5, 1.9×took 5.1 s and 2.6 s | Claude Sonnet 5, 6.1×cost $0.0164 and $0.0027 |
| An email thread in one sentence | Neither passed | Closetook 2.5 s and 2.3 s | Claude Sonnet 5, 5.9×cost $0.0114 and $0.0019 |
| Decisions and action items from a meeting | Both passed | Claude Sonnet 5, 2.0×took 5.6 s and 2.8 s | Claude Sonnet 5, 5.5×cost $0.0182 and $0.0033 |
| A quarterly memo for the CEO | Both passed | Claude Sonnet 5, 1.7×took 5.0 s and 3.0 s | Claude Sonnet 5, 5.7×cost $0.0184 and $0.0033 |
| A study with a negative result | Both passed | Claude Sonnet 5, 1.8×took 4.9 s and 2.7 s | Claude Sonnet 5, 5.7×cost $0.0160 and $0.0028 |
| The region with the most revenue | Both passed | Claude Fable 5.1, 1.6×took 4.1 s and 6.4 s | Claude Sonnet 5, 3.9×cost $0.0159 and $0.0041 |
| Average order value in August | Both passed | Claude Fable 5.1, 1.2×took 3.3 s and 3.9 s | Claude Sonnet 5, 5.1×cost $0.0209 and $0.0041 |
| Revenue change from July to August | Both passed | Closetook 4.9 s and 5.3 s | Claude Sonnet 5, 3.7×cost $0.0232 and $0.0062 |
| A median, filtered two ways | Both passed | Claude Sonnet 5, 1.4×took 6.7 s and 4.9 s | Claude Sonnet 5, 4.2×cost $0.0151 and $0.0036 |
| Correlation between ad spend and sign-ups | Only Claude Fable 5.1 | Closetook 14.2 s and 13.8 s | Claude Sonnet 5, 4.0×cost $0.0663 and $0.0165 |
| A late order | Both passed | Claude Sonnet 5, 1.7×took 6.1 s and 3.5 s | Claude Sonnet 5, 5.6×cost $0.0199 and $0.0036 |
| A return inside the window | Both passed | Claude Sonnet 5, 1.7×took 4.9 s and 2.9 s | Claude Sonnet 5, 5.5×cost $0.0178 and $0.0032 |
| A frustrated customer | Both passed | Claude Sonnet 5, 1.6×took 7.0 s and 4.4 s | Claude Sonnet 5, 5.4×cost $0.0223 and $0.0041 |
| A refund request outside the window | Both passed | Claude Sonnet 5, 1.4×took 4.5 s and 3.2 s | Claude Sonnet 5, 6.5×cost $0.0204 and $0.0031 |
| A message with a planted instruction | Only Claude Sonnet 5 | Claude Sonnet 5, 1.6×took 7.2 s and 4.6 s | Claude Sonnet 5, 7.3×cost $0.0299 and $0.0041 |
| A delivery message into Spanish | Both passed | Claude Sonnet 5, 1.6×took 4.2 s and 2.7 s | Claude Sonnet 5, 5.4×cost $0.0158 and $0.0029 |
| A product description into French | Both passed | Claude Sonnet 5, 2.0×took 5.1 s and 2.5 s | Claude Sonnet 5, 5.5×cost $0.0158 and $0.0029 |
| A meeting note into German | Both passed | Claude Sonnet 5, 1.7×took 4.7 s and 2.8 s | Claude Sonnet 5, 5.7×cost $0.0152 and $0.0027 |
| Idioms into natural Japanese | Both passed | Claude Sonnet 5, 2.1×took 8.5 s and 4.1 s | Claude Sonnet 5, 7.8×cost $0.0217 and $0.0028 |
| A lease clause into Brazilian Portuguese | Both passed | Claude Sonnet 5, 1.5×took 5.6 s and 3.8 s | Claude Sonnet 5, 5.4×cost $0.0192 and $0.0036 |
| Customers in one country | Both passed | Claude Sonnet 5, 1.7×took 3.2 s and 1.8 s | Claude Sonnet 5, 5.9×cost $0.0120 and $0.0020 |
| Count orders by status | Both passed | Claude Sonnet 5, 1.8×took 3.5 s and 2.0 s | Claude Sonnet 5, 6.2×cost $0.0122 and $0.0020 |
| Revenue by category | Both passed | Claude Sonnet 5, 1.3×took 4.5 s and 3.5 s | Claude Sonnet 5, 6.2×cost $0.0190 and $0.0031 |
| Every customer, even those without orders | Both passed | Claude Sonnet 5, 2.4×took 5.2 s and 2.2 s | Claude Sonnet 5, 6.6×cost $0.0199 and $0.0030 |
| Monthly revenue with a running total | Both passed | Claude Sonnet 5, 2.1×took 6.3 s and 3.0 s | Claude Sonnet 5, 7.0×cost $0.0293 and $0.0042 |
| A fact from one section | Both passed | Claude Sonnet 5, 2.1×took 3.5 s and 1.7 s | Claude Sonnet 5, 6.9×cost $0.0134 and $0.0019 |
| Core hours and start times | Both passed | Claude Sonnet 5, 1.8×took 3.7 s and 2.1 s | Claude Sonnet 5, 6.2×cost $0.0135 and $0.0022 |
| Two sections in one answer | Both passed | Claude Sonnet 5, 3.4×took 6.3 s and 1.8 s | Claude Sonnet 5, 6.0×cost $0.0133 and $0.0022 |
| A later amendment changes the answer | Both passed | Claude Sonnet 5, 3.4×took 7.1 s and 2.1 s | Claude Sonnet 5, 6.3×cost $0.0165 and $0.0026 |
| A question the handbook doesn't answer | Both passed | Claude Sonnet 5, 2.2×took 4.0 s and 1.8 s | Claude Sonnet 5, 8.4×cost $0.0160 and $0.0019 |
| Pick the tool and work out the date | Both passed | Claude Sonnet 5, 1.9×took 3.3 s and 1.7 s | Claude Sonnet 5, 5.8×cost $0.0102 and $0.0018 |
| Convert a currency | Both passed | Claude Sonnet 5, 1.8×took 3.5 s and 2.0 s | Claude Sonnet 5, 5.8×cost $0.0103 and $0.0018 |
| Book a meeting from a sentence | Both passed | Claude Fable 5.1, 2.2×took 2.5 s and 5.7 s | Claude Sonnet 5, 3.5×cost $0.0131 and $0.0037 |
| Search, but don't book | Both passed | Claude Sonnet 5, 2.7×took 5.0 s and 1.9 s | Claude Sonnet 5, 5.8×cost $0.0116 and $0.0020 |
| Two calls with a unit conversion | Both passed | Claude Sonnet 5, 1.3×took 4.8 s and 3.8 s | Claude Sonnet 5, 5.1×cost $0.0145 and $0.0028 |
Claude Fable 5.1 vs Claude Sonnet 5 in our test runs
Claude Fable 5.1 and Claude Sonnet 5 on the same prompts, job by job: how many replies passed their check.
Based on 100 of our test runs on , through OpenRouter with the app's own prompt and settings. Updated .
| Job | Claude Fable 5.1 | Claude Sonnet 5 |
|---|---|---|
| Coding | 5 of 5 | 5 of 5 |
| Writing | 3 of 5 | 4 of 5 |
| Math | 5 of 5 | 5 of 5 |
| Summarization | 3 of 5 | 3 of 5 |
| Data analysis | 5 of 5 | 4 of 5 |
| Customer support | 4 of 5 | 5 of 5 |
| Translation | 5 of 5 | 5 of 5 |
| SQL | 5 of 5 | 5 of 5 |
| RAG and answering from documents | 5 of 5 | 5 of 5 |
| Agents and tool use | 5 of 5 | 5 of 5 |
| All jobs | 45 of 50 · 1 message each · $0.0200 a reply | 46 of 50 · 1 message each · $0.0041 a reply |
The same prompts, sent to both through llmwise's own pipeline and checked the same way: five for each job. A bold count is the one that passed more. Messages: what each reply counted as on Pro. Cost: what OpenRouter charged us per reply, on average. Every prompt, and how it's scored.
Where they differed most, writing: both replies to a prompt only one of them passed.
An everyday prompt: “Announce a second bakery shop on LinkedIn”, in full.
Claude Fable 5.1
Passed: Graded 4.8 of 5 on average (lowest 4).
We're opening a second Crumb & Co. When we started baking out of one small shop, we didn't imagine we'd ever need a second oven, let alone a second door. But our customers kept coming back, kept telling their friends, and kept asking whether we might ever open somewhere closer to them. So we listened. On 14 November, Crumb & Co. opens in Leeds. It'll be the same bread, the same pastries, and the same early mornings, just in a new neighbourhood. We've been baking test batches for weeks to make sure the first loaf out of the Leeds oven tastes exactly like the ones you already know. To say thank you, coffee is on us all day on opening day. Come by, have a cup, and try something warm from the counter. We'd love to see you there. Thank you for getting us here.
540 tokens in, 259 out · 7.3 s · $0.0184 · 1 message on Pro · answered by anthropic/claude-fable-5.1 via Anthropic ·
Claude Sonnet 5
Failed: Graded 3.5 of 5 on average (lowest 3).
We have some exciting news to share: Crumb & Co. is opening our second shop, this time in Leeds! From our very first bakery, we've believed in doing simple things well — proper sourdough, honest pastries, and coffee worth stopping for. Now we get to bring that same spirit to a new neighbourhood and, hopefully, a whole new group of familiar faces. Our Leeds shop opens its doors on 14 November, and we'd love for you to be there. To celebrate, every coffee on opening day is on us — no catch, just our way of saying thank you for supporting us along the way. This has been months of planning, a lot of taste-testing, and more excitement than we know what to do with. We can't wait to welcome you in, share some fresh bakes, and start building new memories together. See you there — first coffee's on the house.
538 tokens in, 267 out · 4.6 s · $0.0037 · 1 message on Pro · answered by anthropic/claude-sonnet-5 via Claude Platform on AWS ·
Claude Fable 5.1 and Claude Sonnet 5 on every plan
Whether the one-time free trial reaches each model, then each paid plan's messages on it.
| Plan | Price | Claude Fable 5.1 | Claude Sonnet 5 |
|---|---|---|---|
| Free | $0 | Not in the trial | In the one-time trial of 5 messages |
| Pro | $20 a month | Up to 31 a month | Up to 125 a month |
| Max | $50 a month | Up to 100 a month | Up to 400 a month |
| Ultra | $100 a month | Up to 225 a month | Up to 900 a month |
| Studio | $200 a month | Up to 500 a month | Up to 2,000 a month |
Prices don't include tax, which is added where it applies and shown before you pay. A paid plan's month is one allowance shared by every model, so each monthly count is the most you get if all of it goes to that model. It renews each billing period; everyday models refill daily at 00:00 UTC. Long chats count more per reply. How pricing works.
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
What differs
Messages on Pro
Claude Sonnet 5 gets four times as many messages: up to 125 messages a month on Pro, against up to 31 messages a month for Claude Fable 5.1.
Context window
Both take up to 1M tokens of context. A chat in llmwise holds up to 200k tokens, which fits in either, so the difference shows only through each maker's own API.
Images and PDFs
Both read images. Both take a PDF as the whole file, pages and all.
On Free
Claude Sonnet 5 is in the free trial; Claude Fable 5.1 needs a paid plan.
Where messages go
Both are Claude models, served the same way. Sent to Anthropic directly.
Fact by fact
| Fact | Claude Fable 5.1 | Claude Sonnet 5 |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Reads images | Yes | Yes |
| PDFs | Whole file | Whole file |
| Reasoning | Yes | Yes |
| API price (September 2026) | $10.00 in / $50.00 out per million tokens | $2.00 in / $10.00 out per million tokens |
| A typical message at API prices (4,000 tokens in, 700 out) | $0.0750 | $0.0150 |
| A $10 top-up adds | 25 messages | 100 messages |
| Where a message goes | Sent to Anthropic directly. | Sent to Anthropic directly. |
| If the provider fails | If Anthropic fails before the reply starts (an overload, a server error, a dropped connection), llmwise sends the same request to Claude Fable 5.1 through OpenRouter instead. | If Anthropic fails before the reply starts (an overload, a server error, a dropped connection), llmwise sends the same request to Claude Sonnet 5 through OpenRouter instead. |
| Anthropic's safety fallback | Anthropic's safety system can pass a Claude Fable 5.1 message to another Claude model. The reply then names the model that answered and says what you were charged for. | Doesn't apply |
Claude Fable 5.1 or Claude Sonnet 5?
From the facts above and our test runs: the rest is how their answers suit your work, which one chat can show you.
Pick Claude Sonnet 5: more messages for the money, up to 125 messages a month on Pro; you can try it in the free trial.
Each model's page, the families, and other pairs
Claude Fable 5.1 vs Claude Sonnet 5 is one pair of models. The pages below cover the whole family.
- Claude Fable 5.1: price, limits and messages on every plan
- Claude Sonnet 5: price, limits and messages on every plan
- Claude playground: try Claude online
- Is Claude Fable 5.1 included in Claude Pro?
- Claude Fable 5.1 vs GPT-6 Astra
- Claude Fable 5.1 vs Claude Opus 5.5
- Claude Fable 5.1 vs Kimi K3
- Claude Opus 5.5 vs Claude Sonnet 5
- Claude Sonnet 5.5 vs Claude Sonnet 5
- Claude Sonnet 5 vs Claude Haiku 4.5
- Every model-vs-model page
Both are made by the same company, so they're served the same way.
Questions
Is Claude Fable 5.1 or Claude Sonnet 5 cheaper in llmwise?
Claude Sonnet 5 gets four times as many messages: up to 125 messages a month on Pro, against up to 31 messages a month for Claude Fable 5.1. Every paid plan's monthly allowance is shared by all models, so each count is the most you get if it all goes to that model.
Can I try Claude Fable 5.1 and Claude Sonnet 5 for free?
Claude Sonnet 5 is, in the free trial of 5 messages; Claude Fable 5.1 needs a paid plan.
Which has the bigger context window, Claude Fable 5.1 or Claude Sonnet 5?
Neither: both take 1M tokens. A chat in llmwise holds up to 200k tokens, which fits in either, so the difference shows only through each maker's own API.
Can I use Claude Fable 5.1 and Claude Sonnet 5 in the same chat?
Yes. Pick Claude Fable 5.1 for one message and Claude Sonnet 5 for the next; the second sees the whole chat, including the first one's answer.
Which did better in your test runs, Claude Fable 5.1 or Claude Sonnet 5?
On the same 50 prompts, run on September 27, 2026, Claude Fable 5.1 passed 45 and Claude Sonnet 5 passed 46. The table on this page has each job, and every reply is published.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.