Models
Explore all available models on Privatemode. This page gives you a quick look at each model’s capabilities, modalities, and API endpoint.
Supported models
| Model Name | Model ID | Type | Modality | Context Window | API Endpoint |
|---|---|---|---|---|---|
| Llama 3.3 70B | ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4 | Chat | Text | 70k tokens | /v1/chat/completions, /v1/completions |
| Gemma 3 27B | leon-se/gemma-3-27b-it-fp8-dynamic | Chat | Text, Image | 70k tokens | /v1/chat/completions |
| gpt-oss-120b | openai/gpt-oss-120b | Chat | Text | 90k tokens | /v1/chat/completions, /v1/completions |
| Qwen2.5-Coder 14B | qwen/qwen2.5-coder-14b-instruct-awq | Chat | Text | 32k tokens | /v1/chat/completions, /v1/completions |
| multilingual-e5 | intfloat/multilingual-e5-large-instruct | Embedding | Text | 512 tokens | /v1/embeddings |
| Whisper | openai/whisper-large-v3 | Speech-to-text, Translation | Audio | 25 MB | /v1/audio/transcriptions, /v1/audio/translations |
For endpoint compatibility and usage examples, refer to each model’s detail page.