Together AI / together/tev1-4b-experimental
Tev1 4B Experimental - access through LLMTR
Tev1 4B Experimental is an experimental decision model from Together AI, fine-tuned from Qwen3.5-4B. It does not hold a conversation: you send a state, a question and 2-24 options labelled A to X as JSON, and it returns only the letter of the option it picks, which you map back to your own key. A response is at most 8 tokens, so use temperature 0 and a system message that asks for the letter alone. Input is text only, with a 32,768-token context window. Output tokens are free; only input is billed. Instructions written inside the state can sway the choice, so validate the result when the state contains untrusted text.
Technical specifications
| Canonical ID | together/tev1-4b-experimental |
|---|---|
| Provider | Together AI |
| 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 | $0.042000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | Not available |
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":"together/tev1-4b-experimental","messages":[{"role":"user","content":"Hello"}]}'Related models
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- 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
- EmbeddingGemma 300M llmtr/embeddinggemma-300m
- Qwen 3.5 4B llmtr/qwen3-5-4b