RentGPU RentGPU
Trouver un GPU →
by Deepreinforce Ai

Ornith-1.0-35B.

multimodal open weights 262K ctx
Cheapest input
$0.14/M
on DeepInfra
Cheapest output
$1.0/M
on DeepInfra
Hosted equiv.
~$0.36/hr
@ 100 tok/s on DeepInfra

Ornith-1.0-35B is DeepReinforce's open (MIT-licensed) agentic-coding model: an RL post-train of Qwen3.5-35B-A3B, a 35B-total / ~3B-active Mixture-of-Experts with hybrid Gated-DeltaNet attention. It targets state-of-the-a

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.14 $1.0 Launch ↗
FAQ

Frequently asked.

How do I run Ornith-1.0-35B?
Ornith-1.0-35B is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Ornith-1.0-35B?
Ornith-1.0-35B is available via DeepInfra. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Ornith-1.0-35B?
API pricing starts at $0.14/M input tokens and $1.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Ornith-1.0-35B open-source or proprietary?
Ornith-1.0-35B is open-weight under the license. You can download and self-host it.