Ornith-1.5 35B-A3B
- Family
- Ornith 1.5
- Released
- 2026-08-19
- Context
- 256K
- Parameters
- 35.95B total, ~3B active
- 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
WebsiteCheapest of 1 route · RunInfra · cache read $0.010
About
Ornith-1.5 35B-A3B is the mid-size mixture-of-experts model in DeepReinforce's Ornith-1.5 family (~3B active parameters per token), post-trained with a self-improvement loop for agentic coding. The maker reports 68.5 on Terminal-Bench 2.1 and 79.0 on SWE-Bench Verified. 262,144-token context, OpenAI-style tool calling, MIT license; also served by RunInfra.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| RunInfra | $0.100 | $0.400 | read $0.010 | Serverless |
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
WebsiteCheapest of 1 route · RunInfra · cache read $0.010