Chinese model APIs on one OpenAI-compatible key. Browse models

Europe · bilingual + controls

Budgeted keys per squad

Bilingual Chinese-model access with spend you can audit

European squads usually need bilingual quality checks, clear key ownership and prepaid spend caps before a wider rollout. Keep one Base URL, separate keys per team, and only promote Live DeepSeek routes.

EnglishGermanFrenchSpanishDutchPolish

Europe pilot plan

A region-specific rollout, not a generic template

StepActionSuccess signal
Define languagesPick 2–3 live product languages and write pass/fail rubrics before calling any model.Rubric exists for tone, factuality and refusal cases.
Split keysIssue one budgeted key per squad (support, eng, research).Wallet logs show attributable usage by team.
Promote carefullyKeep production on Live IDs only; document Integrating entries as roadmap.No Integrating ID appears in prod config.

Workload matrix

Where to start for Europe

Bilingual support

deepseek-chat

Cost-efficient drafts; spot-check with native speakers.

Policy / long docs

deepseek-v4-pro

Stronger multi-step answers on the same evidence pack.

Code review

deepseek-chat → V4 Pro escalate

Use Pro only when chat fails the test suite.

Live prices

Only Live DeepSeek routes

ModelBillable price
DeepSeek Flash

deepseek-chat

$0.3 input / $1.2 output per 1M
DeepSeek V4 Pro

deepseek-v4-pro

$1.32 input / $3.96 output per 1M

Integrating catalog families are market context only. Confirm Live status on /models before production.

Support in more than one language

Run identical tickets in English and a local language. Score accuracy and tone before choosing a default Live route.

Audit-friendly key layout

Named keys with daily caps make it easier to explain AI spend in monthly reviews without opening every vendor console.

Privacy-aware rollout posture

Keep customer prompts in approved environments, log request IDs (not secrets), and treat catalog status as part of change control.

Migration

Keep the SDK, change the base URL

  • Write bilingual acceptance rubrics before benchmarking.
  • Separate keys for support vs engineering.
  • Compare deepseek-chat and deepseek-v4-pro on the same ticket set.
  • Document Live vs Integrating in your internal runbook.
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SMTOKEN_API_KEY,
  baseURL: "https://thesmartoken.com/v1",
});

const completion = await client.chat.completions.create({
  model: "deepseek-chat",
  messages: [
    {
      role: "user",
      content: "Draft a English reply for our Europe support pilot.",
    },
  ],
});

FAQ for Europe

Is there an EU-only endpoint?

No. The Base URL remains https://thesmartoken.com/v1. Regional pages describe workloads and operating habits, not separate model clusters.

Can we keep OpenAI-compatible tooling?

Yes. Keep the SDK, set baseURL, authenticate with a SmarToken key, and select a Live model ID.

Which routes are Live?

deepseek-chat and deepseek-v4-pro. Re-check /models and /pricing before procurement quotes.

How should we handle Integrating models?

Treat them as catalog signals during wiring, not production call targets.