PublicAI / publicai/apertus-v1.5-70b
Apertus v1.5 70B - access through LLMTR
Apertus v1.5 70B is the largest model in the family and handles text and image input together. Its 262,144-token context window lets it work through long documents, codebases, and multi-turn conversations in a single request. It produces stronger results than the 8B version on quality-sensitive work such as information synthesis, analysis, multilingual assistant flows, content drafting, and coding help. It supports function calling and JSON-formatted output, so it works with tool-calling code and chat applications. Images must be supplied as base64 data URLs.
Technical specifications
| Canonical ID | publicai/apertus-v1.5-70b |
|---|---|
| Provider | PublicAI |
| Context window | 262,144 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
A 6% 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 | $0.820000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $2.92 |
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":"publicai/apertus-v1.5-70b","messages":[{"role":"user","content":"Hello"}]}'Related models
- Apertus v1.5 8B publicai/apertus-v1.5-8b
- Apertus v1.5 8B Thinking publicai/apertus-v1.5-8b-thinking
- Apertus 8B Instruct publicai/apertus-8b-instruct
- Apertus 70B Instruct publicai/apertus-70b-instruct
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- MedGemma 4B llmtr/medgemma-4b
- Trendyol 7B llmtr/trendyol-7b