Last refreshed 2026-10-22. Next refresh: weekly.
Why use Ornith-1.5 35B-A3B on RunInfra?
RunInfra offers Ornith-1.5 35B-A3B with pay-as-you-go pricing at $0.10/1M input tokens. RunInfra (by RightNow) is a pay-per-token model API for open-weight models with session-aware caching for agent workloads.
Input / 1M
$0.10
Output / 1M
$0.40
Cache
read $0.010
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: ornith-1-5-35bModel ID
ornith-1-5-35bRequest example
Curated snippets for this provider are not sourced yet. Use RunInfra documentation with model ID
ornith-1-5-35b.Gotchas
- Use provider model ID "ornith-1-5-35b", not the LLMReference slug "ornith-1.5-35b-a3b".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.10 |
| Output tokens | $0.40 |
Capabilities
ReasoningJSON / Tool use
About Ornith-1.5 35B-A3B
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.
Get Started
Model Specs
Released2026-08-19
Parameters35.95B total, ~3B active
Context256K
ArchitectureMixture of Experts