Costs

For 18 of the 19 models with a price per character, only the source characters count, so we know the cost of a text before we translate it. For the remaining character-billed model, output characters also affect the price. With token billing, the translation counts too. Its tokens are ~88% of the cost at the median (75% to 90% by model), so the cost depends on how long the translation is and on how many tokens per character the tokenizer of the model produces.

Anthropic Claude Sonnet 5 costs $4.52 per million characters into Chinese and $11.13 into Burmese. Across 23 models with billing on tokens, Lao, Odia and Amharic cost ~2.3 times as much as the median language.

At the median, a solution on an MT engine costs $24.99 per million characters and on an LLM $4.59, and MT engines cost more than LLMs in all 96 languages. Prices run from $0.11 on the open-weight Google Gemma 4, at the lowest price of an inference provider, to $100 on ALL-Lab, an MT engine.

Translations from MT engines have a median 58 errors per 1,000 words weighted by severity, against 31 from LLMs, and more errors in 79 of the 84 languages with an Intento LQA result for both. 0% of the MT engine solutions meet every Standard requirement, against 12% of the LLM solutions.

Within each type, the price follows the quality. In 43 of the 46 languages with three or more MT engine solutions, the more expensive MT engines have fewer errors, as DeepL Next Gen and Translated Lara 2 against Microsoft Translator, and in 79 of 82 languages, the more expensive LLMs.

Per word, the median solution costs ~$0.00006, while in the 2025 edition we priced human translation at $0.16 to $0.24 per word, ~2,700 to 4,100 times as much.

See details →

The three-step median is ~30 times the two-step median and ~110 times the adjusted-LLM median. A one-step solution costs a median $27.50 per million characters on an off-the-shelf MT engine, LLM-based MT engines included, and $5.20 on an adjusted LLM. Tone of voice and a glossary in the request add ~2.5% to the cost of an LLM translation and nothing to an MT engine with a price per source character. A two-step solution (translation + post-edit) costs ~2.5 times as much as the one-step solution it starts from.

In a three-step solution (translation + LQA + repair), ~96% of the cost is the Intento LQA step, where we send every sentence to three LLM judges and their findings to a fourth LLM that combines them. A gender-neutral version costs a few percent more to translate than the solution it is a version of, and ~$1,000 as a three-step solution, gender checks included.

Each range covers several models and up to 96 languages. With billing on tokens, the same text costs more in languages with a longer translation and more tokens per character, so the ranges depend on the languages as well as on the models.

We use unified billing in Intento Language Hub to estimate costs across these model-and-harness workflows, including the Intento LQA step.

See details →

We compare the cheapest solution that meets the requirements of each quality level in the same languages, those where two solutions meet every Advanced requirement. In most of them, the cheapest solution that meets general translation quality (no critical error, at most three major errors and at most 20 weighted errors per 1,000 words) also meets the other Standard requirements, or meets them as a two-step solution (translation + repair by code) at no extra cost.

In Marathi and Thai, only three-step solutions (translation + LQA + repair) meet the Standard requirements, at ~$550 per million characters against $8.20 and $21.28 for the Basic requirements.

Meeting the Advanced requirements costs 10 times as much or more in four languages, such as Telugu ($29.87 to $929 per million characters). We check gender neutrality only on the two best solutions of each language, those with the fewest errors, so the cheapest solution that meets the Advanced requirements often runs on a more expensive model or takes more steps.

Where the gender-neutrality agent works with a three-step solution, its gender checks add ~$400 per million characters, as in Amharic ($612 to $1,043).

See details →

It costs from $0.11 per million characters in Indonesian, on Google Gemma 4, to $39.95 in Georgian, on Anthropic Claude Fable 5, with a median of $5.54. In 11 of them, it runs on Google Gemini 3.1 Pro. Within a language, the most expensive one-step solution that meets every Standard requirement costs ~6 times as much as the cheapest at the median, against ~80 times among all one-step solutions on the shortlist.

See details →

On the open-weight Google Gemma 4 and Alibaba Cloud Qwen3, it costs $0.11 to $1.10, with Gemma 4 at the lowest price of an inference provider and Qwen3 at the last price on the Alibaba Cloud price list. Among LLMs, Anthropic Claude Fable 5 costs the most, $32.84 at the median, and among MT engines, ALL-Lab, $100. LLM-based MT engines, such as DeepL Next Gen and Translated Lara 2, cost ~5 times the median LLM.

See details →

We call a solution real-time when we get the translation of a text in 2 seconds or less. Every real-time solution with a cost runs on an MT engine (DeepL Next Gen, Translated Lara 2, Microsoft Translator, Google Translation LLM, Google Cloud Advanced Translation API or Amazon), at $10 to $27.50 per million characters, and it costs more than the other solutions in 95 of 96 languages.

The fastest LLM solution with a cost, OpenAI GPT-5.6 Luna in Portuguese (European), takes 8.6 seconds per text. OpenAI gpt-oss-120b, an open-weight LLM, is real-time in 20 languages, but we have no token count for its translations, so it has no cost in our results.

0% of the real-time solutions meet every Standard requirement, and only DeepL Next Gen in German and Romanian meets general translation quality (no critical error, at most three major errors and at most 20 weighted errors per 1,000 words).