Apertus 1.5 8B
Apertus 1.5 8B is available now for rag, agents, and long context with open-source and 262k context; evaluate it while provider pricing coverage matures.
- Family
- Apertus
- Released
- 2026-07-24
- Context
- 262k
- Parameters
- 8B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Multi-stage
No tracked provider token pricing is available yet.
About
Apertus 1.5 8B (HF swiss-ai/Apertus-v1.5-8B) is the laptop-scale model in the Swiss AI Initiative's fully open Apertus 1.5 release (24 July 2026). It continues Apertus 1.0 8B pretraining on another 4T tokens of text and multimodal data; post-training runs SFT, RLVR, DPO and a final Charter-alignment (SDPO) stage. It takes text, image and audio (experimental) input and outputs text, with a 262,144-token context, an optional thinking mode and tool calling. Released under Apache 2.0 behind an auto-approved Hugging Face click-through.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
swiss-ai/Apertus-v1.5-8BApertus 1.5 8Bswiss-ai/apertus-v1.5-8b (Public AI)swiss-ai/apertus-v1.5-8b-thinking (Public AI)No tracked provider token pricing is available yet.