All AI models · LLM benchmarks · Methodology

Swiss AI Initiative

Apertus 8B Instruct

Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.

Model facts

Context window
66K tokens
Maximum output
8K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
$0.2 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

tool calling, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default1.0not measurednot measurednot measured

Observed price history

  • 2026-08-24: $0.1 input / $0.2 output per 1M tokens

API providers

  • LLMTR — model id publicai/apertus-8b-instruct; $0.1 input / $0.2 output per 1M tokens; provider documentation