# SMS length > How many SMS messages will your text take? Characters, encoding and message parts, counted the way phone networks do. Count how many SMS parts a text needs. See whether it fits GSM-7 or switches to UCS-2, which characters count double and how much room is left. - Page: https://how.box/sms-length/ - Runs entirely in the browser. - License: HowToolbox's own text and data (titles, explanations, FAQs, tool descriptions and schemas, this file) are CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/); AI training and answers are welcome. Attribute "HowToolbox (how.box)" with a link to the page used. Third-party data keeps its own terms; the name and logo are not licensed. Publisher: HowToolbox, contact@how.box. Terms: https://how.box/about/terms/ ## Inputs Answer link: https://how.box/sms-length/? Example answer: https://how.box/sms-length/? The page computes the answer in the browser: read results from the agent tools below, not from the page HTML. ## Agent tools - `sms_length_count`: Counts SMS parts for a text (3GPP TS 23.038/23.040). - MCP, one POST to https://how.box/mcp: `{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"sms_length_count","arguments":{}}}` - GET: https://how.box/mcp/run/sms_length_count ## How it works An SMS carries 140 bytes. Phone networks pack plain text into the GSM 7-bit alphabet, so one message holds 160 characters. A few symbols (^ { } \ [ ~ ] | and €) live in an extension table and take two of those 7-bit units each. A single character outside that alphabet, such as an emoji, a curly quote or a Cyrillic letter, switches the whole message to UCS-2, which uses 16 bits per unit: then one message holds only 70. An emoji and some rarer characters take two units. A longer text is sent in parts, and each part spends 6 bytes on a header that lets the phone join them, so a part holds 153 GSM-7 units or 67 UCS-2 units. A character is never split between two parts. The rules come from the 3GPP specifications TS 23.038 (alphabets): https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=745 and TS 23.040 (message parts): https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=747. Some phones replace characters before sending or use national shift tables (for example Turkish or Portuguese), and operators bill each part, so the count can differ slightly from what a particular phone shows. ## FAQ **Why did my message suddenly take three parts?** One character outside the GSM-7 alphabet, often an emoji or a curly apostrophe, switches the whole message to UCS-2, where a part holds 67 instead of 153. **Are Finnish, Swedish and German letters safe?** Ä, ö, å, ü and ß are in the GSM-7 alphabet. Letters such as š, ž or õ are not, so they switch the message to UCS-2. **Why does the euro sign count twice?** It is in the GSM-7 extension table, sent as an escape code plus the character, so it takes two units. **Is my text sent anywhere?** No. It is counted on this device and never enters the page address or a shared link. **Do spaces and line breaks count toward the SMS limit?** Yes. Each space and each line-feed character uses one unit; a pasted line ending containing both a carriage return and a line feed uses two. More: [HowToolbox index](https://how.box/llms.txt) · [Agent Skill](https://how.box/skill.md) · [agent terms](https://how.box/about/agents/)