Liquid AI / liquid/lfm-2.5-24b-a2b
LFM2.5-24B-A2B - access through LLMTR
LFM2.5-24B-A2B is Liquid AI's mixture-of-experts language model with 24B total and about 2B active parameters per token, trained for tool calling and multi-step agent tasks. It takes text input only, offers a 128,000-token context and can return structured output that follows a JSON schema. It reasons before every answer and this cannot be turned off: reasoning tokens bill as output and count toward the 8,192-token output limit per response. On long tasks reasoning can use that entire limit; split the work into smaller steps. Turkish is not among the languages Liquid officially supports.
Technical specifications
| Canonical ID | liquid/lfm-2.5-24b-a2b |
|---|---|
| Provider | Liquid AI |
| Context window | 128,000 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 | $0.050000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.025000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $0.700000 |
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":"liquid/lfm-2.5-24b-a2b","messages":[{"role":"user","content":"Hello"}]}'Related models
- LFM2.5-Embedding-350M (free) liquid/lfm-2.5-embedding-350m-free
- 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