Models — Available AI Models
General Models
| Name | Display Name | Input | Output | Use Cases |
|---|---|---|---|---|
| llama-3-70b | Llama 3 70B | text | text | Conversational AI, Chatbots, QA, Content Generation |
| gemma-3-27b | Gemma 3 27B | text, image | text | Multimodal understanding, VQA, Doc analysis, Math, Translation |
| gemini-2-5-pro | Gemini 2.5 Pro | text, image, audio, video | text | Complex reasoning, Code, Scientific analysis, Multimodal content |
| gemini-2-5-flash | Gemini 2.5 Flash | text, image, audio, video | text | Real-time chat, Quick analysis, Fast generation |
| gemini-2-5-flash-lite | Gemini 2.5 Flash Lite | text, image | text | Mobile apps, Edge, Low-latency responses |
| deepseek-r1 | DeepSeek R1 | text | text | Complex problem solving, Math reasoning, Code, Research |
| kimi-k2 | Kimi K2 | text | text | Long document analysis, Conversational AI, Summarization |
| gpt-5 | GPT-5 | text, image, audio | text, image | Advanced reasoning, Creative content, Code, Research |
| gpt-5-nano | GPT-5 Nano | text, image | text | Mobile/edge, Quick responses, Embedded systems |
| gpt-oss-20b | GPT OSS 20B | text | text | Agentic apps, Function calling, Structured outputs |
| gpt-oss-120b | GPT OSS 120B | text | text | High-reasoning tasks, Production systems, Agentic workflows |
| grok-4 | Grok-4 | text, image | text | Complex analysis, Real-time info, Research |
Medical Models
| Name | Display Name | Input | Output | Privacy | Use Cases |
|---|---|---|---|---|---|
| medgemma-4b-it | MedGemma 4B IT | text, image | text | true | Medical doc analysis, CDS, Imaging analysis, Chatbots |
| medgemma-4b-it:pro | MedGemma 4B IT Pro | text, image, video | text | true | Advanced imaging, Radiology reports, Pathology, Multi-image |
| medgemma-27b-it | MedGemma 27B IT | text, image | text | true | Advanced medical analysis, Research, Imaging, Literature review |
| medgemma-27b-it:pro | MedGemma 27B IT Pro | text, image, video | text | true | Expert imaging analysis, Complex diagnostics, Multimodal |
| lingshu-32b | Lingshu 32B | text | text | true | Medical documentation, CDS, Medical reasoning |
| lingshu-32b:pro | Lingshu 32B Pro | text, image | text | true | Advanced imaging, Complex diagnostics, Research |
| lingshu-7b | Lingshu 7B | text | text | true | Medical chatbots, Quick queries, Mobile apps |
| lingshu-7b:pro | Lingshu 7B Pro | text, image | text | true | Mobile imaging, Telemedicine, Edge diagnostics |
| biomistral-7b | BioMistral 7B | text | text | true | Biomedical research, Clinical documentation, Drug discovery |
| biomistral-7b:pro | BioMistral 7B Pro | text, image | text | true | Microscopy, Pathology, Molecular analysis |
Notes
- Model classes: GENERAL or MEDICAL
- Task types include: text generation, image-text-to-text, text-to-image, embeddings, feature extraction
- Choose
gpt-oss-120bfor general high-reasoning; choosemedgemma-27bfor healthcare tasks