IFM (MBZUAI) / ifm/k2-horizon-375b-a23b
K2 Horizon 375B A23B - access through LLMTR
K2 Horizon 375B A23B is an open-weight mixture-of-experts (MoE) model released under Apache 2.0 by MBZUAI's Institute of Foundation Models (IFM), with 375 billion total and 23 billion active parameters. Its context window is 524,288 tokens and it accepts text only. Tool calling, JSON mode and structured output with JSON Schema are supported. The model reasons before every answer and reasoning cannot be turned off; reasoning_effort selects medium or high. Reasoning tokens count toward max_tokens, so a short max_tokens can cut the answer off before reasoning ends. It is free until 5 November 2026, 23:59 (TRT), with a daily token allowance.
Technical specifications
| Canonical ID | ifm/k2-horizon-375b-a23b |
|---|---|
| Provider | IFM (MBZUAI) |
| Context window | 524,288 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 | Not available |
| 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":"ifm/k2-horizon-375b-a23b","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- K2 Horizon vs DeepSeek V4 Pro, GLM-5.3, Nemotron 3 Ultra - All four models are called on LLMTR with the same API key through /v1/chat/completions. K2 Horizon is free until 5 November 2026, 23:59 (TRT) and reasons before every answer. The free option with no end date is Nemotron 3 Ultra. On the paid side, DeepSeek V4 Pro costs less than GLM-5.3 outside peak hours.
- The K2 Horizon API: a 375B-parameter open-weight model - On LLMTR, K2 Horizon is called at https://llmtr.com/v1/chat/completions under the id ifm/k2-horizon-375b-a23b. It is IFM's Apache 2.0 model with 375 billion total and 23 billion active parameters; it reasons before every answer and carries a 524,288-token context. It is free until 5 November 2026, 23:59 (TRT), with a daily token allowance.
- reasoning_effort and max_tokens on K2 Horizon - On LLMTR, K2 Horizon does not turn reasoning off; reasoning_effort selects medium or high, and low, none and minimal return 400. Because reasoning tokens count toward max_tokens, a short limit can leave the answer empty; when finish_reason is length, retry with a higher limit. The model is free with a daily allowance until 5 November 2026.
- Jais 3 or K2 Horizon? Choosing between IFM's two models - Jais 3 and K2 Horizon are models from the same maker, MBZUAI's IFM, and on LLMTR both come with a 524,288-token context, free with a daily allowance until 5 November 2026. Jais 3 is for Arabic and English, 36B (4B active); K2 Horizon is 375B (23B active) and reasons before every answer. Forcing a tool works only on K2 Horizon.
- Arabic models on LLMTR: Jais 3, Jais ASR and K2 Horizon - In October 2026 three models from MBZUAI's IFM were added to LLMTR: ifm/jais-3-mova-36b-a4b for Arabic and English chat, ifm/jais-asr for Arabic recordings, and ifm/k2-horizon-375b-a23b, which reasons before every answer. All three are free with a daily allowance until 5 November 2026, 23:59 (TRT), and are retired on 6 November.
Related models
- Jais 3 MoVA 36B A4B ifm/jais-3-mova-36b-a4b
- Jais ASR ifm/jais-asr
- 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