Best AI model to translate text
Translating websites, documents and messages. The catalog sources have no translation score, so the list shows the text models people actually use most, which is not a quality score.
Suggested models
No translation score in the catalog sources. The order follows real usage on OpenRouter.
1 DeepSeek V4.1 Flash DeepSeek
Why it fits: Accounts for 32.17% of tokens on OpenRouter, a sign that many people use it at volume. Usage shows adoption, not translation quality.
- Real usage: 32.17% of OpenRouter tokens?what it is · GPQA Diamond: 93.2%, per Epoch AI, latest version we checked?
- Price: US$ 0.022 input and US$ 0.40 output per 1M tokens (source: OpenRouter)?
- Estimated cost (see the How we calculate block): about US$ 0.0011 (estimate)
- Weights: Open?
- Alternative: already the cheapest or open option on this list
2 Hy4 Tencent
Why it fits: Accounts for 10.74% of tokens on OpenRouter, a sign that many people use it at volume. Usage shows adoption, not translation quality.
- Real usage: 10.74% of OpenRouter tokens?
- Price: US$ 0.42 input and US$ 1.25 output per 1M tokens (source: OpenRouter)?
- Estimated cost (see the How we calculate block): about US$ 0.0044 (estimate)
- Weights: Open?
- Alternative: DeepSeek V4.1 Flash, cheaper: US$ 0.022 input per 1M tokens, 93.2% on GPQA Diamond
3 GLM-5.3-Flash Zhipu AI (Z.ai)
Why it fits: Accounts for 5.09% of tokens on OpenRouter, a sign that many people use it at volume. Usage shows adoption, not translation quality.
- Real usage: 5.09% of OpenRouter tokens? · GPQA Diamond: 90.2%, per Epoch AI, latest version we checked?
- Price: US$ 0.04 input and US$ 0.078 output per 1M tokens (source: OpenRouter)?
- Estimated cost (see the How we calculate block): about US$ 0.00032 (estimate)
- Weights: Open?
- Alternative: already the cheapest or open option on this list
4 GPT-6 Luna OpenAI
Why it fits: Accounts for 3.42% of tokens on OpenRouter, a sign that many people use it at volume. Usage shows adoption, not translation quality.
- Real usage: 3.42% of OpenRouter tokens? · GPQA Diamond: 90.5%, per Epoch AI, latest version we checked?
- Price: US$ 0.10 input and US$ 0.50 output per 1M tokens (source: OpenAI, official page)?
- Estimated cost (see the How we calculate block): about US$ 0.0016 (estimate)
- Weights: Closed?
- Alternative: DeepSeek V4.1 Flash, with open weights, 93.2% on GPQA Diamond
Order: real usage on OpenRouter, by share of tokens. Usage is not a quality score.
How we calculate
Change the numbers and the cost of every model on the page is recalculated right away. Without JavaScript, the default values below apply.
Input and output = words ÷ 0.75, assuming the translation is the same length as the source.
With these numbers: about 2,667 input tokens and 2,667 output tokens (estimate).
Conversion used: 1 token is about 4 characters or 0.75 words, OpenAI's rough rule for English text. Other languages can differ. Conversion source: OpenAI, Understanding and counting tokens
Cost of each model = input tokens × input price + output tokens × output price, with prices per 1M tokens. Models that reason before answering can use many more output tokens. It is a reference calculation and does not change the order of the list.
Other paid models we checked
Reference paid models from the main labs. They are left out of the list above because of a lower score, no score on this metric, or not passing the case filter. Prices come from the company's official page when it publishes them.
| Model | Score on this metric | Price and source | Estimated cost |
|---|---|---|---|
| GPT-6 Astra OpenAI | 95.8% | US$ 10.00 input and US$ 50.00 output per 1M tokens (source: OpenAI, official page) | about US$ 0.16 (estimate) |
| GPT-6.1 Sol OpenAI | 95.4% | US$ 2.00 input and US$ 10.00 output per 1M tokens (source: OpenAI, official page) | about US$ 0.032 (estimate) |
| Claude Fable 5.2 Anthropic | 93.9% | US$ 8.00 input and US$ 40.00 output per 1M tokens (source: Anthropic, official page) | about US$ 0.13 (estimate) |
| Claude Opus 5.5 Anthropic | 90.6% | US$ 4.00 input and US$ 20.00 output per 1M tokens (source: Anthropic, official page) | about US$ 0.064 (estimate) |
| Claude Sonnet 5.5 Anthropic | 95.6% | US$ 2.00 input and US$ 10.00 output per 1M tokens (source: Anthropic, official page) | about US$ 0.032 (estimate) |
| Claude Haiku 5.5 Anthropic | 89.6% | US$ 0.10 input and US$ 0.50 output per 1M tokens (source: Anthropic, official page; up to 100,000 prompt tokens) | about US$ 0.0016 (estimate) |
| Gemini 4 Argon Google | 96.4% | US$ 2.00 input and US$ 10.00 output per 1M tokens promotional price (source: Google, official page; promotional price currently shown on the page; Google has said this price will go up) | about US$ 0.032 (estimate) |
| Gemini 3.8 Flash Google | 95.4% | US$ 0.75 input and US$ 3.75 output per 1M tokens promotional price (source: Google, official page; promotional price currently shown on the page; Google has said this price will go up) | about US$ 0.012 (estimate) |
| Grok 4.7 xAI | 92.7% | US$ 2.00 input and US$ 6.00 output per 1M tokens (source: xAI, official page) | about US$ 0.021 (estimate) |
| Mistral Large 4 Mistral AI | 90.2% | US$ 0.50 input and US$ 1.50 output per 1M tokens (source: Mistral AI, official page; price the official page gives for Mistral Large, without naming the version) | about US$ 0.0053 (estimate) |
| Mistral Medium 3.5 Mistral AI | no score on this metric | US$ 1.50 input and US$ 7.50 output per 1M tokens (source: OpenRouter; the price could not be read from the official page, because the table is built automatically; OpenRouter is kept as the reference) | about US$ 0.024 (estimate) |
| Command A Cohere | no score on this metric | US$ 2.50 input and US$ 10.00 output per 1M tokens (source: OpenRouter; Cohere's official page does not publish this model's price; OpenRouter is kept as reference) | about US$ 0.033 (estimate) |
| Command A+ Cohere | no score on this metric | US$ 0.30 input and US$ 1.50 output per 1M tokens (source: OpenRouter; Cohere's official page does not publish this model's price; OpenRouter is kept as reference) | about US$ 0.0048 (estimate) |
| Nova Premier 1.0 Amazon | no score on this metric | US$ 2.50 input and US$ 12.50 output per 1M tokens (source: Amazon, official page; us-east-1 region, official AWS price list) | about US$ 0.04 (estimate) |
| Nova 2 Lite Amazon | no score on this metric | US$ 0.33 input and US$ 2.75 output per 1M tokens (source: Amazon, official page; us-east-1 region, official AWS price list) | about US$ 0.0082 (estimate) |
FAQ
What is the best AI model to translate text?
By this page's rule, the list starts with DeepSeek V4.1 Flash, Hy4, GLM-5.3-Flash, GPT-6 Luna. Order: real usage on OpenRouter, by share of tokens. Usage is not a quality score.
How much does it cost to translate text with AI?
With the default values in the How we calculate block, the estimate ranges from US$ 0.00032 to US$ 0.0044 among the listed models with a published price. It is only an estimate and you can adjust the numbers on the page.
Is there an open weights option to translate text?
Yes: DeepSeek V4.1 Flash, Hy4, GLM-5.3-Flash.
Does this page use AI to recommend?
No. The recommendation comes from fixed rules over public data from Epoch AI, OpenRouter, Hugging Face and each company's official pricing page, in the latest version we checked. The typed text is only compared with keywords.
Terms used on this page
Use cases with their own page
Official pricing pages checked
Sources
- Epoch AI, CC BY 4.0, latest version we checked.
- OpenRouter Benchmarks, CC BY 4.0, latest version we checked.
- OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
- Hugging Face Hub, metadados públicos do Hub; licença de cada modelo no repositório, latest version we checked.
Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.