Deepreinforce: Ornith 1.0 397B

Large coding-reasoning model for agentic software tasks and RL search

Model lab: Deepreinforce
Model family: ornith

Model resources

Model card Announcement Hugging Face Hugging Face (FP8)

Modalitiestext, image → text

Context window262,144

Maximum output—

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to deepreinforce/ornith-1.0-397b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "deepreinforce/ornith-1.0-397b"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Ornith 1.0 397B API Pricing

Price currently unavailable

Benchmarks

Benchmark	Score	Measurement
SWE-Bench Verified	82.4	percent resolved
SWE-Bench Pro	62.2	percent resolved
SWE-Bench Multilingual	78.9	percent resolved
Terminal-Bench 2.1	77.5	percent · Variant: Terminus-2
Terminal-Bench 2.1	78.2	percent · Variant: Claude Code
NL2Repo	48.2	percent
Claw-eval	77.1	percent

Performance

Performance trends

Throughput92.6 tok/sCurrent

Time to first token1.2 sCurrent

End-to-end latency7.5 sCurrent

Throughput

Current92.6 tok/s

Window average89.1 tok/s

Time to first token

Current1.2 s

Window average1.5 s

End-to-end latency

Current7.5 s

Window average7.5 s

Tail latency (P99)

Current15.1 s

Window average16.6 s

Prompt cache hit rate

Current26.1%

Window average24.0%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Ornith 1.0 397B Compare models

Model	Input price	Output price	Context window	Capabilities
Ornith 1.0 397BThis page	Price currently unavailable	Price currently unavailable	262,144	Text output · Reasoning · Tool calling
Ornith 1.5 35B A3B	USD 0.08 / 1M tokens	USD 0.32 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Ornith 1.0 9B	Price currently unavailable	Price currently unavailable	262,144	Text output · Reasoning · Tool calling
Ornith 1.0 31B	Price currently unavailable	Price currently unavailable	262,144	Text output · Reasoning · Tool calling
DeepSeek V4.1 Flash 1017	USD 0.028 / 1M tokens · Quantization fp4	USD 0.4 / 1M tokens · Quantization fp4	1,000,000	Text output · Reasoning · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 262,144
Maximum output: —
Release date: 2026-06-25
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Ornith 1.0 397B for?

Large coding-reasoning model for agentic software tasks and RL search

What inputs and outputs does Ornith 1.0 397B support?

Recorded inputs: text, images; outputs: text.

How is Ornith 1.0 397B priced?

This page does not list a price for this model yet.

What specifications are recorded for Ornith 1.0 397B?

Current model records list Context window 262,144 tokens.

What model parameter does the Quickstart use?

The example uses deepreinforce/ornith-1.0-397b. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.