LLMTR / llmtr/medgemma-4b
MedGemma 4B - access through LLMTR
LLMTR MedGemma 4B is hosted in Turkey and positioned for medical text plus single-image understanding from base64 data URLs; remote image URLs are not supported. The MedGemma multimodal family uses a SigLIP image encoder pre-trained on de-identified medical imagery such as chest X-rays, dermatology, ophthalmology, and histopathology, while its language component is trained on medical text, QA, and medical image/data sources. Outputs are not intended to directly inform diagnosis, treatment, or patient management without independent clinical verification. Because the model is called infrequently, the first request also waits for the model to load and can take minutes; consecutive requests are noticeably faster. Use `stream: true` and raise your client read timeout to at least 300 seconds.
Technical specifications
| Canonical ID | llmtr/medgemma-4b |
|---|---|
| Provider | LLMTR |
| Context window | 8,192 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $3.00 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $5.00 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions \
-H "Authorization: Bearer llmtr-your_key" \
-H "Content-Type: application/json" \
-d '{"model":"llmtr/medgemma-4b","messages":[{"role":"user","content":"Hello"}]}'Related models
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Trendyol 7B llmtr/trendyol-7b
- Magibu 11B v8 llmtr/magibu-11b-v8
- EmbeddingGemma 300M llmtr/embeddinggemma-300m
- Qwen 3.5 4B llmtr/qwen3-5-4b
- Ornith 1.0 35B llmtr/ornith-1-35b
- GPT-5.6 Sol openai/gpt-5.6-sol