
ornith-ai/Ornith-1.5-35B-A3B-FP8
A 35B MoE reasoning model with 3B active parameters, optimized for agentic coding, tool use, and 256K-context workflows in FP8.
Ornith-1.5-35B-A3B is a 35B-parameter mixture-of-experts reasoning model from Ornith AI that activates roughly 3B parameters per token. Optimized for agentic coding, complex reasoning, and tool-driven workflows, its FP8 weights reduce memory requirements for more efficient deployment.
The model supports a native 256K-token context window, structured reasoning, and function calling. It is well suited to repository-scale code understanding, software engineering agents, automation, and other long-context tasks.
| Attribute | Value |
|---|---|
| Parameter Size | 35B-A3B |
| Context Length | 256k |
| Input Modalities | Text, Image (single) |
| Output Modalities | Text |
| Supported Features | Tool Use Structured Output Reasoning |
Input
import os
from openai import OpenAI
model_id = os.environ["BASETEN_MODEL_ID"]
client = OpenAI(
api_key=os.environ["BASETEN_API_KEY"],
base_url=(
f"https://model-{model_id}.api.baseten.co/"
"environments/production/sync/v1"
)
)
response = client.chat.completions.create(
model="Ornith-1.5-35B-A3B",
messages=[{
"role": "user",
"content": "Write a one-line Python lambda that squares a number."
}],
temperature=0.6,
top_p=0.95,
max_tokens=1024,
)
message = response.choices[0].message
# reasoning_content holds the <think> trace; content holds the final answer.
print("reasoning:", getattr(message, "reasoning_content", None))
print("answer:", message.content)