LibreTranslate
AGPL-licensed, self-hostable machine translation API built on Argos Translate (OpenNMT/CTranslate2); paid hosted keys also offered.
You can run LibreTranslate on your own hardware without per-character fees. Budget for hosting and maintenance, and test language quality before replacing another engine. The throughput estimate here is 1–2 million characters an hour on an L4/T4-class GPU; real performance depends on the language pair. Hosted keys start at $14/month, with unlimited characters subject to rate limits.
- Headquarters
- 🇺🇸 United States
- Parent jurisdiction
- 🇺🇸 United States
- EU self-serve plan
- Available; check eligible plans and regions
- GDPR DPA
- No / not documented
- Billing
- self-hosted
- Open source
- Yes · self-hostable
- Website
- libretranslate.com
- Source last checked
- 2026-10-06
- Pricing evidence
- Operating cost not estimated
Pricing
Operating cost not estimated · servers, licenses and engineering time are yours. See notes for software editions and license terms.
Free software: budget for hosting and maintenance. Rough estimate: a single L4/T4-class GPU translates on the order of 1-2M characters/hour with the Argos models (CPU-only on 4-8 vCPU works at a fraction of that), so 50M chars/month fits on one small GPU or a couple of CPU instances. Quality is noticeably below DeepL, Google and current LLMs for many language pairs. Hosted API keys on libretranslate.com: Starter $14/month, Pro $29/month, Business $58/month, unlimited characters but rate-limited (sustained ~6, 20 and 50 calls/minute of up to 2,000 characters each, i.e. roughly 0.7M, 2.4M and 6M chars/hour). EU residency and DPA apply only to your own deployment.
Managed alternatives
At 50M characters / month. Adjust usage and requirements.
LibreTranslate has no bill to estimate: you pay for the servers, storage and time to run it. The cheapest managed option here is GPT-6 Luna (via OpenAI API) at $111/yr, so running LibreTranslate yourself saves money only if hosting and upkeep stay below about $9.25 a month.
- GPT-6 Luna (via OpenAI API): $111/yr estimatedModeled ratesToken-to-character conversion assumes English source, short prompts and European-language output. Quality and retries are not priced.
- Qwen3.8-Flash (via Alibaba Cloud Model Studio): $116/yr estimatedModeled ratesToken-to-character conversion assumes English source, short prompts and European-language output. Quality and retries are not priced.
- Mistral Small 4 (via Mistral API): $140/yr estimatedModeled ratesToken-to-character conversion assumes English source, short prompts and European-language output. Quality and retries are not priced.
- DeepSeek V4 Flash (via DeepSeek API): $279/yr estimatedModeled ratesToken-to-character conversion assumes English source, short prompts and European-language output. Quality and retries are not priced.
- Gemini 3.1 Flash-Lite (via Gemini API): $323/yr estimatedModeled ratesToken-to-character conversion assumes English source, short prompts and European-language output. Quality and retries are not priced.
No cheaper managed estimate matches your filters. Adjust your usage or compare with your actual contract bill.
The price difference leaves out migration costs, operating costs and any features you’d need to replace.
Self-hosted options
Operating cost is not estimated. These options are not counted as savings against managed services.
Want a European-owned provider? See European alternatives to LibreTranslate among european machine translation providers.
Other machine translation comparisons
- DeepL API vs Google Cloud Translation
- DeepL API vs Azure AI Translator
- Google Cloud Translation vs Amazon Translate
Found a wrong rate or plan restriction? Report a correction with a current source.