SUTRA-R0 Guide
Welcome to the Build with SUTRA-R0 guide — designed to help developers leverage the advanced reasoning capabilities of SUTRA-R0 in AI agents, decision engines, and complex workflows.
What is SUTRA-R0?
SUTRA-R0 is the first in our series of advanced reasoning models, designed for complex problem-solving and deep contextual understanding. Built to analyze, infer, and generate logical responses, SUTRA-R0 goes beyond pattern recognition—applying structured reasoning to tackle nuanced queries, multi-step problem-solving, and enterprise decision-making. Its architecture enables high-accuracy responses across domains, making it a powerful tool for knowledge-intensive workflows and next-generation AI applications.
SUTRA-R0 is an advanced reasoning model trained to perform Multi-step logical inference, Structured problem-solving and Deep contextual analysis. Following are some example scenarios for which R0 is ideal choice
| Scenario | Example |
|---|---|
| Legal Analysis | Interpret multi-clause statements and policies |
| Scientific Reports | Break down cause-effect chains in data |
| Complex Q&A | Multi-hop reasoning across large corpora |
| Business Logic Automation | Analyze structured decisions and optimize workflows |
Getting Started with SUTRA-R0
SUTRA-R0's API is fully compatible with OpenAI’s specifications, supporting seamless integration for developers. To begin using the SUTRA-R0 API, install the required package:
# SUTRA models are OpenAI API compatible
!pip install -qU openaiAuthenticate with your API key:
from openai import OpenAI
client = OpenAI(
base_url='https://api.two.ai/v2',
api_key="YOUR_SUTRA_API_KEY"
)Make a basic structured reasoning request:
response = client.chat.completions.create(
model='sutra-r0',
messages=[
{"role": "user", "content": "If Alice is taller than Bob, and Bob is taller than Carol, who is the tallest?"}
],
max_tokens=512,
temperature=0.3
)
print(response.choices[0].message.content)Comparative Reasoning Example
def compare_reasoning(prompt):
basic = client.chat.completions.create(
model='sutra-r0',
messages=[{"role": "user", "content": prompt}],
temperature=0.3
)
advanced = client.chat.completions.create(
model='sutra-r0',
messages=[{"role": "user", "content": prompt}],
temperature=0.7,
presence_penalty=0.6
)
print("Basic reasoning:\n", basic.choices[0].message.content)
print("\nAdvanced reasoning:\n", advanced.choices[0].message.content)
compare_reasoning("Explain the trade-offs between nuclear and solar energy for long-term policy decisions.")Recommended Parameters
| Parameter | Purpose | Recommended for R0 |
|---|---|---|
temperature | Controls determinism | 0.3–0.5 for logic |
max_tokens | Limits response length | 512–1024 |
presence_penalty | Penalize repeating info | 0.3–0.7 |
API Access (cURL)
curl -X POST https://api.two.ai/v2/chat/completions \
-H "Authorization: Bearer $SUTRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sutra-r0",
"messages": [
{"role": "user", "content": "Explain how blockchain improves supply chain transparency."}
]
}'