LLMTR / llmtr/nanbeige4-2-3b
Nanbeige4.2 3B - access through LLMTR
Nanbeige4.2 3B is a small chat model we host in Turkey; requests are never forwarded to a third-party provider. It suits short summaries, classification and tool-calling flows with few steps. The prompt and the answer share a 32,768-token context window. Text input only. `response_format` is not supported; use tool calling for structured output. Thinking is off by default; `:think` or `reasoning: true` turns it on. When you send `tools`, thinking is turned on for that request; a request that turns thinking off while sending `tools` is refused. `tool_choice` accepts only `auto`. Answers are generated slowly: use streaming and set your client timeout to at least 300 seconds. Without `max_tokens` the answer stops at 4,096 tokens. A repeated prompt prefix can be served from cache; only tokens reported as `cached_tokens` are billed at the discounted rate. The model is trained mostly on English and Chinese; ask for Turkish in the system message.
Technical specifications
| Canonical ID | llmtr/nanbeige4-2-3b |
|---|---|
| Provider | LLMTR |
| Context window | 32,768 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text |
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 | $1.00 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.250000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $3.00 |
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/nanbeige4-2-3b","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Nanbeige4.2 3B vs Ministral 3 3B: two small models - Both models are called on LLMTR through /v1/chat/completions with the same API key. Nanbeige4.2 3B is hosted in Turkey and costs $1.00 input and $3.00 output per 1M tokens. Ministral 3 3B costs $0.10 input and $0.10 output, reads images and does not carry LLMTR's Turkey hosting mark.
- Nanbeige4.2 3B vs Qwen 3.8 27B: two Turkey-hosted models - Nanbeige4.2 3B and Qwen 3.8 27B are both hosted in Turkey on LLMTR and are called through /v1/chat/completions with the same API key. Nanbeige4.2 3B costs $1.00 input and $3.00 output per 1M tokens. Qwen 3.8 27B costs $5.00 input and $7.00 output and offers a 262,144-token context and JSON schema output.
- Turkish text classification: Nanbeige4.2 3B or Leyla? - Nanbeige4.2 3B and Leyla are both hosted in Turkey on LLMTR and are called with the same API key. Leyla answers the questions you define on /v1/systemone with a choice, a score or a yes-probability, at $0.03 per 1M input tokens. Nanbeige4.2 3B, on /v1/chat/completions, also writes a reason or a summary next to the label, at $1.00 input and $3.00 output.
- Nanbeige4.2 3B vs GPT-5 nano: choosing a small model - Both models are called on LLMTR through /v1/chat/completions with the same API key. Nanbeige4.2 3B is hosted in Turkey and costs $1.00 input and $3.00 output per 1M tokens. GPT-5 nano costs $0.05 input and $0.40 output, reads images and does not carry LLMTR's Turkey hosting mark. OpenAI shuts GPT-5 nano down on 11 December 2026; after that date GPT-6 Luna can be used on LLMTR.
Related models
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Qwen 3.8 27B llmtr/qwen3-8-27b
- Trendyol Asure 12B llmtr/trendyol-asure-12b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Muse Glimmer 30B (Turkey) llmtr/muse-glimmer-30b-tr
- Leyla llmtr/leyla
- EmbeddingMagibu 200M llmtr/embeddingmagibu-200m