Models
Open models, served in [Insert: city].
Released by their makers for anyone to run, served on our GPUs. Every one behind the same API.
| Model | Maker | For | Context |
|---|---|---|---|
| gpt-oss-120b | OpenAI | Reasoning | 128k |
| DeepSeek V4 Flash | DeepSeek | Chat | [Insert] |
| GLM-5.3-Flash | Z.ai | Chat | [Insert] |
| Llama 3.1 8B | Meta | Small and fast | 128k |
| SEA-LION | AI Singapore | Southeast Asian languages | [Insert] |
| BGE-M3 | BAAI | Embeddings | 8k |
[Insert: launch models — six candidates shown]
See every priceMissing a model?
Tell our team which one, and what you would run on it.