LLM Reference

K2 Horizon 0.9B

Released
2026-09-03
Last refreshed
2026-09-07
Status
Researched today
Open sourceCommercial use: permittedRAGAgentsLong contextClassificationJSON / Tool use

K2 Horizon 0.9B is available now for rag, agents, and long context with open-source and 131k context; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating rag, agents, and long context
  • Workloads that can use a 131k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Teams that need a tracked hosted API route today
Specifications
Released
2026-09-03
Context
131k
Parameters
0.9B
Architecture
Decoder Only
Specialization
agentic
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by

Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) is the world's first graduate-level, research-focused A

Abu Dhabi, UAE
Founded 2019
Website
Pricing

No tracked provider token pricing is available yet.

About

K2-Horizon-0.9B is the compact dense K2 Horizon model: 0.9B parameters with 128K context via YaRN RoPE scaling (131,072 tokens), multi-teacher distillation across math, code, STEM, and instruction following, and Apache 2.0 weights on Hugging Face (IFM/K2-Horizon-0.9B).

Top use-case fit: coding, agents, and build tasks

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

ReasoningJSON / Tool useStructured Outputs

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.