The Coding Model That Actually Gets It

Deploy models where your data lives, with security, visibility, and ownership built in.

In coalition with

alan-turingbabcockbaebthsbclloydstelefonicaleonardolsegpwc
alan-turingbabcockbaebthsbclloydstelefonicaleonardolsegpwc
alan-turingbabcockbaebthsbclloydstelefonicaleonardolsegpwc
alan-turingbabcockbaebthsbclloydstelefonicaleonardolsegpwc
sovereign-ai-coalition

Major UK Institutions join Cosine's Sovereign AI coalition

Cosine has assembled a coalition of leading UK defense, infrastructure, financial, healthcare, and technology leaders to develop Sovereign AI.

Read the announcement

Real benchmarks. Real results.

Lumen is optimized for the outcomes that matter: shipping better code, faster, with fewer headaches.

42.4%

GPT-5.4

44.9%

Gemini 3.1 Pro

47.4%

GPT-5.5

48.3%

Kimi K2.6

59.3%

Lumen Outpost

Read more about Niche-Bench
Lumen video thumbnail

Our thesis: specialists outperform generalists

Most AI models try to be everything to everyone. They write poetry, solve physics problems, and summarise novels.

Lumen does one thing: write exceptional software.

Our thesis is simple. A model trained exclusively on real production code, from real engineering teams will always beat a generalist at the task developers actually need.

That's why every training decision, every optimization, every evaluation metric is grounded in a single objective: better code.

Less AI Slop

Optimized for maintainability, readability, and production-quality outputs, not bloated code generation.

Built for Real Systems

Designed to reason across complex architectures, legacy infrastructure, and long-lived codebases.

Beyond Mainstream Languages

Post-trained for enterprise and niche languages including COBOL, Fortran, Verilog, Rust, and complex SQL.

Use Cosine wherever you work

Start in your terminal

Start in your terminal

Work within a terminal-native interface, with a local-to-remote execution model, external tool access via MCP, and multi-agent orchestration.

Collaborate in the Cloud

Collaborate in the Cloud

Run multiple coding tasks in parallel, plan large changes and collaborate across engineers, PMs, and stakeholders in a shared project.

Enterprise Deployment

Built to fit your security environment


Start quickly in Cosine Cloud, or move into a dedicated tenant or fully air-gapped deployment when your infrastructure, data, and compliance requirements demand it.

Public Cloud

Fully managed Cosine for teams whose requirements fit our standard cloud controls.

Managed single-tenant cloud

A private Cosine environment operated for your organization with enterprise controls.

Fully air-gapped

For organisations that need Cosine to run entirely inside their own security perimeter.

Model family

Three models. One philosophy.

Lumen isn't a single model — it's a system designed for every layer of the development workflow.

ScoutPost-trained from Devstral 123B

Runs cheaply, operates on-device, and handles the heavy lifting around the coding loop.

Scout8B — in-repo, fast
OutpostLarge code support workflow
FrontierNo kVA
Context window
Files
247
Symbols
1.2k
History
48h

Ready to start building?

Get started with Cosine today.