Machine translation

Qwen3.8-Flash (via Alibaba Cloud Model Studio)

Translation with Alibaba's small Qwen3.8-Flash model on Model Studio (international), priced from token rates.

Singapore token rates give an estimated $0.19 per million characters. Non-English sources and non-Latin targets can use more tokens. Alibaba Cloud offers a DPA and batch discounts, but this model does not have EU-only inference: Frankfurt offers Global scope, which stores data in the region but can process requests elsewhere.

Pricing

Published rates converted using workload assumptions. Read the notes. Token-to-character conversion assumes English source, short prompts and European-language output. Quality and retries are not priced. How to read these estimates.

Derived from International (Singapore) token prices: $0.15 per 1M input tokens, $0.47 per 1M output tokens. 0.35 x $0.15 + 0.30 x $0.47 = $0.0525 + $0.141 = $0.19 per 1M characters. Assumptions (shared by all LLM-derived rows): English source at ~4 characters per token, so 1M characters = 250k source tokens; a ~200-token prompt per 2,000-character chunk adds 500 x 200 = 100k tokens, giving 350k input tokens per 1M characters; output for European target languages ~1.2x the source = 300k tokens. Cost per 1M characters = 0.35 x input price + 0.30 x output price (per 1M tokens). Non-Latin target languages (CJK, Arabic, Hindi) and non-English sources can use noticeably more tokens. Batch calls are discounted. Frankfurt lists qwen3.8-flash ($0.113 / $0.382) only with "Global" deployment scope: requests are stored in Frankfurt but inference can run on any node, including outside the EU. EU-scope inference is offered only for a subset of models (e.g. qwen3.5-flash at $0.10 / $0.40).

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.