LLM Reference

Ornith-1.0 397B

Released
2026-06-25
Last refreshed
2026-06-27
Status
Researched today
Open sourceCommercial use: permittedCodingRAGAgentsLong contextJSON / Tool use

Ornith-1.0 397B is available now for coding, rag, and agents with open-source and 262k context; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 262k 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
2026-06-25
Context
262k
Parameters
397B
Architecture
Mixture of Experts
Specialization
coding
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Training
Fine-tuned
Created by

DeepReinforce is an AI research company specializing in reinforcement learning methods for language models. Known for th

Website
Pricing

No tracked provider token pricing is available yet.

About

Ornith-1.0 397B MoE is DeepReinforce's flagship public coding agent model. Trained with self-scaffolding RL, the model designs and refines its own execution harness during training rather than relying on a fixed scaffold, enabling stronger generalization across diverse agentic coding tasks. Available in BF16 (deepreinforce-ai/Ornith-1.0-397B) and FP8 quantized (deepreinforce-ai/Ornith-1.0-397B-FP8) on Hugging Face. Official DeepReinforce and Hugging Face sources report a SWE-Bench Verified score of 82.4. Context: 262,144 tokens.

Ornith-1.0 397B is an open-source model in the Ornith 1.0 family. The structured metadata tracks a 262k-token context window, reasoning, function calling, and tool use. No headline benchmark score is tracked for Ornith-1.0 397B yet.

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

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

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

ReasoningFunction CallingTool Use

Benchmark peer barsfor Coding

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

Migration checks

No linked migration route is available for this model yet.