Ornith-1.5 397B
Ornith-1.5 397B is available now for coding, rag, and agents with open-source and 256K context; evaluate it while provider pricing coverage matures.
- Family
- Ornith 1.5
- Released
- 2026-08-19
- Context
- 256K
- Parameters
- 403.4B total (397B MoE)
- Architecture
- Mixture of Experts
- Specialization
- coding
- Openness
- Open source
- License
- MITOSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
DeepReinforce, now publicly branded as Ornith, is an AI research company specializing in reinforcement learning methods
WebsiteNo tracked provider pricing is available yet.
About
Ornith-1.5 397B is the flagship mixture-of-experts model of DeepReinforce's Ornith-1.5 family, post-trained with a self-improvement loop (task generation, scaffold construction and solution rollouts). The maker reports 86.1 on Terminal-Bench 2.1 and 56.0 on DeepSWE. 262,144-token context, OpenAI-style tool calling, MIT license.
Providers
No active provider routes are tracked for this model yet.
Capabilities
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.
DeepReinforce, now publicly branded as Ornith, is an AI research company specializing in reinforcement learning methods
WebsiteNo tracked provider pricing is available yet.