| Whisper Large v3 | audio | text | - | 8,192 | | 2023-09 |
| Voxtral Small 24B 2507 | text, audio | text | 32,000 | 16,384 | 🔧 | - |
| Qwen3.5 397B A17B | text, image, video | text | 256,000 | 16,384 | 🧠 🔧 | 2025-04 |
| Qwen3 Embedding 8B | text | text | 32,768 | 4,096 | | - |
| Qwen3-Coder 30B-A3B Instruct | text | text | 128,000 | 32,768 | 🔧 | 2025-04 |
| Qwen3 235B A22B Instruct 2507 | text | text | 260,000 | 16,384 | 🔧 | - |
| Pixtral 12B 2409 | text, image | text | 128,000 | 4,096 | 🔧 | - |
| Mistral Small 3.2 24B Instruct (2506) | text, image | text | 128,000 | 32,768 | 🔧 | - |
| Mistral Nemo Instruct 2407 | text | text | 128,000 | 8,192 | 🔧 | - |
| Llama-3.3-70B-Instruct | text | text | 100,000 | 16,384 | 🔧 | 2023-12 |
| Llama 3.1 8B Instruct | text | text | 128,000 | 16,384 | 🔧 | 2023-12 |
| GPT-OSS 120B | text | text | 128,000 | 32,768 | 🔧 | - |
| Gemma-3-27B-IT | text, image | text | 40,000 | 8,192 | 🧠 🔧 | 2024-12 |
| Devstral 2 123B Instruct (2512) | text | text | 256,000 | 16,384 | 🔧 | - |
| DeepSeek R1 Distill Llama 70B | text | text | 32,000 | 8,196 | 🧠 🔧 | 2024-07 |
| BGE Multilingual Gemma2 | text | text | 8,191 | 3,072 | | - |
