Skip to content

Prices LLM usage as you go

Model Performance and Pricing

Note

All prices are in USD per 1,000 tokens. MMLU scores indicate model performance on the Massive Multitask Language Understanding benchmark.

High Performance Models

ModelInputOutputMMLUDetails
llama3-swiss 🇨🇭$0.015$0.04585.2%Advanced, Efficient, Recommended
gpt-4o$0.045$0.0992.3%Leading Performance
claude-sonnet$0.005$0.0288.7%Multilingual, Writing, Coding

Balanced Models

ModelInputOutputMMLUDetails
llama-swiss-medium 🇨🇭$0.005$0.0179.2%Strong for Size
mixtral-swiss-big 🇨🇭$0.01$0.02N/AAdvanced Multilingual
mistral-medium$0.00375$0.0112577.3%Efficient, Multilingual
mixtral-swiss-medium 🇨🇭$0.003$0.0177.3%Efficient, Multilingual
gpt-4$0.045$0.0986.5%Consistent
claude-opus$0.022$0.1086.8%Strong Reasoning

Efficient Models

ModelInputOutputMMLUDetails
gpt-3.5-turbo-1106$0.0015$0.003~70%Legacy
mistral-tiny$0.00042$0.0012660.1%Compact, Fast, Cost-Effective
mistral-small$0.0012$0.003670.6%Balanced Speed/Quality

Performance Notes

  • MMLU scores marked with (1) indicate single-shot performance
  • Scores marked with (5-shot) use few-shot learning
  • N/A indicates pending benchmark data

MMLU scores

While MMLU scores provide a useful metric for comparing language model capabilities, they represent only one dimension of performance. These scores primarily measure how well models can handle a standardized set of tasks, but they do not fully capture broader skills such as multilingual comprehension, information retention, domain-specific usage, programming proficiency, or complex reasoning abilities. In practice, different tasks place different demands on a model’s underlying architecture and training data, causing performance to vary considerably across these domains. As a result, MMLU should be seen as a helpful indicator rather than a definitive measure of a model’s overall quality or suitability for a given application. Source: Llm leaderboard

Rate Limiting

All endpoints have a combined limit of CHF 50 per month. If you would like to increase it, please contact support with your estimated usage and use case.