LI
LightOn
Embedding model · France ·Feb 2026

LateOn-Code

Embedding Open Weights
130M
Parameters
8.2K
Context

About LateOn-Code

LateOn-Code is an AI model developed by LightOn, in the embedding category, released in 2026, made available as an open-weights model with 0.1B params. Late-interaction (ColBERT-style) multi-vector retrieval model specialized for code search, built on LightOn's improved M.

On this page you'll find LateOn-Code's full specifications, including a context window of 8.2K tokens. Review provider pricing and benchmark scores below, or compare LateOn-Code head-to-head with other embedding models.

Community

Would you run LateOn-Code again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like LateOn-Code

Frequently asked questions

What is LateOn-Code?

Late-interaction (ColBERT-style) multi-vector retrieval model specialized for code search, built on LightOn's improved M It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created LateOn-Code?

LateOn-Code was developed by LightOn and released in 2026.

Is LateOn-Code open source or proprietary?

LateOn-Code ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

What is LateOn-Code's context window?

LateOn-Code supports a context window of 8.2K tokens, and has 0.1B params.

How much does LateOn-Code cost?

Pricing for LateOn-Code depends on the provider. See the providers table on this page for the latest API rates.

How does LateOn-Code perform on benchmarks?

Benchmark scores for LateOn-Code are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about LateOn-Code?