AionLabs / aion-labs/aion-2.5
AionLabs: Aion 2.5 - access through LLMTR
Aion 2.5 is a roleplay-focused model aimed at more natural responses and faster turns than Aion 2.0. It is useful for preserving character voice, building scene tension, keeping tone across long conversations, and producing creative prose. It supports a 128K context window, 32K max output, and cache-read pricing.
Technical specifications
| Canonical ID | aion-labs/aion-2.5 |
|---|---|
| Provider | AionLabs |
| Context window | 131,072 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text |
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 | $1.00 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.350000 |
| 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":"aion-labs/aion-2.5","messages":[{"role":"user","content":"Hello"}]}'Related models
- AionLabs: Aion 3.0 aion-labs/aion-3.0
- AionLabs: Aion 3.0 Mini aion-labs/aion-3.0-mini
- AionLabs: Aion 2.0 aion-labs/aion-2.0
- AionLabs: Aion-RP 1.0 (8B) aion-labs/aion-rp-llama-3.1-8b
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- MedGemma 4B llmtr/medgemma-4b
- Trendyol 7B llmtr/trendyol-7b