Translate 84% cheaper than Google Cloud Translation
Translate English product and support text into your reader's language. SIE, an open-source inference engine, serves the open translation models Hy-MT2 1.8B and MADLAD-400 3B behind one API.
SIE Hy-MT2 1.8B
Android 13 cutoff keptStarting in Android 13, apps that you install need your permission to send notifications. Tap to change this permission for existing apps.
Android 13以降では、インストールしたアプリが通知を送信するにはあなたの許可が必要です。既存のアプリのこの許可を変更するにはタップしてください。
Android 13 以降では、インストールするアプリに、通知を送信する権限を付与する必要があります。既存のアプリのこの権限を変更するには、タップしてください。
Google Cloud Translation changed 30 to 300 and bills $20 per 1M characters
Google Cloud Translation
30 became 300Let's ride that one over there. Whoa, whoa, whoa, big boy! You're a little too hefty for this ride. Safety first, eh? 30 bills? What a rip-off. I told you. Watch your step!
চলো ওইটায় চড়ি। আরে, আরে, আরে, বড়সড় ছেলে! এই রাইডের জন্য তুমি একটু বেশিই ভারী। আগে নিরাপত্তা, তাই না? ৩০০ ডলার? কী ডাকাতি! আমি তো আগেই বলেছিলাম। সাবধানে পা ফেলো!
In English: 300 dollars
চলো, ওইখানে রাইডটায় চড়া যাক। ওহ, ওহ, ওহ, বিগ বয়! তুমি এই রাইডের জন্য একটু বেশিই ভারী। নিরাপত্তা সবার আগে, তাই না? ৩০টা বিল? এ তো দিনেদুপুরে ডাকাতি! বলেছিলাম তোমায় আমি। সাবধানে চলো!
In English: 30 bills
Google Cloud Translation
$20 per 1M characters- Characters billed
- 341,589 in 1,488 segments
- Bill for 1B characters
- $20,000
- NBC New York Norway's Olympic chefs ordered 1,500 eggs through Google Translate and got 15,000
15,000 Eggs Delivered to Norwegian Olympic Team After Google Translate Error
When a truck load arrived, they learned “a translation error converted their order of 1,500 eggs to 15,000 eggs.”
- arXiv:2107.08357 Findings of ACL 2021 Study: major commercial translation systems get numbers wrong, in high- and low-resource languages
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation
“We find that numerical mistranslation is a general issue”
84% cheaper than Google Cloud Translation
- Tested
- WMT24++: 1,488 segments in 31 locales
- Scored
- chrF++ against the post-edited human reference
- Prices
- Google list price; SIE at its Serverless price
Name the language, get the translation back in one call
from sie_sdk import SIEClientclient = SIEClient(api_key="API keysk-sie-…")text = "textStarting in Android 13, apps that you install need your permission to send notifications. Tap to change this permission for existing apps."result = client.generate( "modeltencent/Hy-MT2-1.8B", f"<｜hy_begin▁of▁sentence｜><｜hy_User｜>Translate the following text into Japanese. Note that you should only output the translated result without any additional explanation: {text}<｜hy_Assistant｜>", max_new_tokens=256, temperature=0,)print(result["text"])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient(undefined, { apiKey: 'sk-sie-…' });
const text = "Starting in Android 13, apps that you install need your permission to send notifications. Tap to change this permission for existing apps.";
const result = await client.generate(
'tencent/Hy-MT2-1.8B',
`<｜hy_begin▁of▁sentence｜><｜hy_User｜>Translate the following text into Japanese. Note that you should only output the translated result without any additional explanation: ${text}<｜hy_Assistant｜>`,
{ maxNewTokens: 256, temperature: 0 },
);
console.log(result.text);curl https://api.superlinked.com/v1/generate/tencent__Hy-MT2-1.8B \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"prompt\":\"<｜hy_begin▁of▁sentence｜><｜hy_User｜>Translate the following text into Japanese. Note that you should only output the translated result without any additional explanation: Starting in Android 13, apps that you install need your permission to send notifications. Tap to change this permission for existing apps.<｜hy_Assistant｜>\",\"max_new_tokens\":256,\"temperature\":0}"Build the "Translation" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: tencent/Hy-MT2-1.8B (SIE primitive: /generate). Keep the model id configurable.
Task
- Input: a block of English text plus the target locale.
- Behaviour: return the text translated into the selected target language
- Call the selected SIE primitive once per request and map the response into your domain type.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.Translate on Serverless, or keep every string in your own cloud
SIE Serverless
We host the models; you call one API.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Self-host the same open-source engine
- SOC 2 Type 2, US or EU data residency
- Create an account to try Serverless
SIE Cluster
Kubernetes in your own cloud, backed by our engineers.
- Terraform modules for your cloud
- Apache-2.0, same engine as Serverless
- GPU workers scale to zero between jobs
- Separate worker pools for each tenant
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment. SIE Local
The open-source server on your own machine.
- NVIDIA GPU
- One container, no cluster
- Process your data fully offline
- Same SDK and model IDs as Serverless
docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-sglang