LLMTR / llmtr/trendyol-asure-12b
Trendyol Asure 12B - access through LLMTR
Trendyol Asure 12B is a 12B chat model produced by Trendyol and hosted in Turkey. With a 40,960-token context window it fits Turkish chat, RAG chatbots, customer-support assistants, e-commerce knowledge flows, summarization, product descriptions, and category or tagging work. It can read images: image input is sent as a base64 data URL, and remote image URLs are not accepted. Repeated prompt prefixes are served from cache and billed at the lower cache rate. Audio and video input, image generation, and tool calling are not supported.
Technical specifications
| Canonical ID | llmtr/trendyol-asure-12b |
|---|---|
| Provider | LLMTR |
| Context window | 40,960 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 | $0.100000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.025000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $0.500000 |
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/trendyol-asure-12b","messages":[{"role":"user","content":"Hello"}]}'
Related models
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- MedGemma 4B llmtr/medgemma-4b
- 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
- Trendyol 7B llmtr/trendyol-7b