Apertus 8B
Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.
- Capability
- —No ECI score yet
- Input
- $0.10per 1M tokens
- Output
- $0.20per 1M tokens
- Context
- 66K8K max output
What it costs
- Input
- $0.10per million tokens
- Output
- $0.20per million tokens
- Blended (3:1)
- $0.125cheaper than 88% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.30 |
| Team assistant25M input + 5M output tokens | $3.50 |
| Production app250M input + 50M output tokens | $35.00 |
Median of 1 paid API provider on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Apertus 8B yet.
The details
- Lab
- Swiss AI
- Released
- Sep 2, 2025
- Knowledge cutoff
- Sep 2025
- Context window
- 65,536 tokens
- Max output
- 8,192 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights · Apache-2.0
- Availability
- 1 API providerlisted on models.dev
More from Swiss AI
About Apertus 8B
How much does Apertus 8B cost?
Apertus 8B costs $0.10 input / $0.20 output per million tokens (median across 1 API provider). At a 3:1 input-to-output mix that is $0.125 per million tokens, cheaper than 88% of the 360 priced models we track.
What is the context window of Apertus 8B?
Apertus 8B accepts up to 65,536 tokens per request and can write up to 8,192 tokens in one response.
How good is Apertus 8B?
Epoch AI has not published a Capabilities Index score for Apertus 8B yet.
Is Apertus 8B open source?
Yes. Swiss AI publishes the weights under the Apache-2.0 licence, so it can be downloaded and self-hosted.
What inputs does Apertus 8B support?
Apertus 8B accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Apertus 8B released?
Swiss AI released Apertus 8B on Sep 2, 2025. Its training data runs to Sep 2025.
What are the best alternatives to Apertus 8B?
The closest current models from other labs on capability, price and release date are Granite-4.0-H-Small (IBM, $0.064 / $0.265), Qwen Flash (Alibaba (Qwen), $0.05 / $0.40), Voxtral Small 24B 2507 (Mistral AI, $0.10 / $0.30) and Sarvam 105B (Sarvam AI, $0.047 / $0.186).