LLM Reference

DeepReinforce

3 models across 1 family · Latest: Ornith-1.0 9B (2026-06)

CodingRAGAgentsLong contextJSON / Tool use

DeepReinforce's portfolio covers 3 active models across 1 current family, spanning coding, rag, and agents. Open a model detail page to compare provider routes and sourced benchmarks.

Covers 5 workload areas across 3 active tracked models; last verified 2026-06-27.

Use it for

  • Teams evaluating coding, rag, and agents across this lab's releases
  • Comparing model families before committing to a flagship
  • Migration and pricing follow-ups across 3 tracked models

Do not use it for

  • Choosing a hosting provider without opening a model page for price ladders

Active models

3

Current models from this lab, excluding deprecated ones

Active families

1

Current model families from this lab

Open catalog

3 open

3 open source / 0 open weights

Lowest output price

Not tracked

No provider output pricing linked yet

Latest dated release

2026-06-25

Ornith-1.0 9B

Freshness

2026-06-27

Researched today

fresh

Information

Links

Website

Release cadence

Showing 3 recent dated releases (full timeline below). Latest: Ornith-1.0 9B (2026-06-25).

Where this lab wins

  • Coding: 3 tracked models with SWE-bench / HumanEval-style scores.
  • RAG: 3 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 3 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 3 tracked models with context-token or InfiniteBench-class signal.

Flagship quality / price signal

Flagship: Ornith-1.0 9B (best sourced coding quality-per-dollar in this portfolio).

Quality-per-dollar unavailable for this flagship — benchmark coverage or output token pricing is still missing.

DeepReinforce is an AI research organization. DeepReinforce ships 1 model family totaling 3 models, with the most recent release Ornith-1.0 9B in 2026-06. Notable families include Ornith 1.0. Use it as a stable reference for lab background, release coverage, and follow-up model pages as they are added. Researchers and evaluators can scan counts, links, release history, and source references without leaving the. View official API endpoints, benchmark performance, and coding/agent fit for every DeepReinforce model.

About

DeepReinforce is an AI research company specializing in reinforcement learning methods for language models. Known for the Ornith model family, which introduces self-scaffolding RL: during training, models jointly learn to design their own execution harness and solution rather than relying on a hand-engineered scaffold. First public release: Ornith 1.0, June 2026.

Featured models

ModelReleasedContextInput price ($/1M)Output price ($/1M)LicenseOpenness
Ornith-1.0 9B2026-06-25262k--MITOpen source
Ornith-1.0 35B2026-06-25262k--MITOpen source
Ornith-1.0 397B2026-06-25262k--MITOpen source

Model families

Recent releases

  1. Ornith-1.0 9B- 2026-06-25
  2. Ornith-1.0 35B- 2026-06-25
  3. Ornith-1.0 397B- 2026-06-25

FAQ

What models has DeepReinforce released?

DeepReinforce ships 3 models across 1 family: Ornith 1.0.

Is DeepReinforce's technology open source?

All tracked models are released under MIT.

How can I access DeepReinforce's models?

DeepReinforce's provider availability is tracked on model pages as API and hosting data is verified.

Explore related pages

Last reviewed: 2026-06-27. Data sourced from public lab announcements and provider documentation.