Raon-1 mini preview

Released
2026-10-21
Last refreshed
2026-10-21
Status
Researched today
Open sourceCommercial use: permittedRAGAgentsLong contextJSON / Tool use

Raon-1 mini preview is a released rag, agents, and long context model with open-source and 256K context; evaluate it while provider pricing coverage matures.

KRAFTON releases · 1 in the last 12 monthsChangelog →
Specifications
Family
Raon
Released
2026-10-21
Context
256K
Parameters
30B
Architecture
Mixture of Experts
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by

KRAFTON is a South Korean video game company whose KRAFTON AI unit builds its own models, including the Raon family of o

Website
Pricing

No tracked provider pricing is available yet.

About

Raon-1 mini preview is a preview of KRAFTON AI's Raon-1 mini, a 30-billion-parameter mixture-of-experts language model with about 4 billion active parameters, designed and trained from scratch, released October 21, 2026. It targets Korean conversation and agentic tasks, supports tool calling and a 262,144-token context, and KRAFTON says it matches Muse Glimmer on coding and agentic tasks while running faster. Weights are on Hugging Face under Apache 2.0 behind an automatic access gate, and a free playground is open for a limited time.

Providers

No active provider routes are tracked for this model yet.

Capabilities

JSON / Tool use

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.

API versions

KRAFTON/Raon-1-mini-previewraon-1-mini-preview