DeepSeek-R1 model post-trained by Perplexity AI to remove censorship and bias while preserving reasoning strength.

R1 1776 API Usage
Endpoint
RUN INFERENCE
curl -X POST "https://api.together.xyz/v1/chat/completions" \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity-ai/r1-1776",
"messages": [{"role": "user", "content": "What are some fun things to do in New York?"}]
}'
JSON RESPONSE
RUN INFERENCE
from together import Together
client = Together()
response = client.chat.completions.create(
model="perplexity-ai/r1-1776",
messages=[{"role": "user", "content": "What are some fun things to do in New York?"}]
)
print(response.choices[0].message.content)
JSON RESPONSE
RUN INFERENCE
import Together from "together-ai";
const together = new Together();
const response = await together.chat.completions.create({
messages: [{"role": "user", "content": "What are some fun things to do in New York?"}],
model: "perplexity-ai/r1-1776"
});
console.log(response.choices[0].message.content)
JSON RESPONSE
Model Provider:
Perplexity AI
Type:
Chat
Variant:
Parameters:
671B
Deployment:
✔️ Serverless
Quantization
Context length:
128K
Pricing:
$3 input / $7 output
Run in playground
Deploy model
Quickstart docs
Quickstart docs
How to use R1 1776
Reasoning models are trained very differently from their non-reasoning counter parts, and as a result they serve different purposes. Below we'll compare both types of models, details for reasoning models, pros and cons, applications and example use-cases.
Reasoning models like R1 1776 are specifically developed to engage in extended, deep analysis of complex challenges. Their strength lies in strategic thinking, developing comprehensive solutions to intricate problems, and processing large amounts of nuanced information to reach decisions. Their high precision and accuracy make them particularly valuable in specialized fields traditionally requiring human expertise, such as mathematics, scientific research, legal work, healthcare, financial analysis.
Non-reasoning models such as Llama 3.3 70B or DeepSeek-V3 are trained for efficient, direct task execution with faster response times and better cost efficiency.
Your application can leverage both types of models: using R1 1776 to develop the strategic framework and problem-solving approach, while deploying non-reasoning models to handle specific tasks where swift execution and cost considerations outweigh the need for absolute precision.
Reasoning models excel for tasks where you need:
- High accuracy and dependable decision-making capabilities
- Solutions to complex problems involving multiple variables and ambiguous data
- Can afford higher query latencies
- Have a higher cost/token budget per task
Non-reasoning models are optimal when you need:
- Faster processing speed(lower overall query latency) and lower operational costs
- Execution of clearly defined, straightforward tasks
- Function calling, JSON mode or other well structured tasks
Model details
R1 1776 is a DeepSeek-R1 reasoning model that has been post-trained by Perplexity AI to remove Chinese Communist Party censorship. The model provides unbiased, accurate, and factual information while maintaining high reasoning capabilities.
Evals
To ensure our model remains fully “uncensored” and capable of engaging with a broad spectrum of sensitive topics, we curated a diverse, multilingual evaluation set of over a 1000 of examples that comprehensively cover such subjects. We then use human annotators as well as carefully designed LLM judges to measure the likelihood a model will evade or provide overly sanitized responses to the queries.

We also ensured that the model’s math and reasoning abilities remained intact after the decensoring process. Evaluations on multiple benchmarks showed that our post-trained model performed on par with the base R1 model, indicating that the decensoring had no impact on its core reasoning capabilities.

Prompting R1 1776
Prompting R1 1776, and other reasoning models in general, is quite different from working with non-reasoning models.
Below we provide guidance on how to get the most out of R1 1776:
- Clear and specific prompts: Write your instructions in plain language, clearly stating what you want. Complex, lengthy prompts often lead to less effective results.
- Sampling parameters: Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs. Also, a top-p of 0.95 is recommended.
- No system prompt: Avoid adding a system prompt; all instructions should be contained within the user prompt.
- No few-shot prompting: Do not provide examples in the prompt, as this consistently degrades model performance. Rather, describe in detail the problem, task, and output format you want the model to accomplish. If you do want to provide examples, ensure that they align very closely with your prompt instructions.
- Structure your prompt: Break up different parts of your prompt using clear markers like XML tags, markdown formatting, or labeled sections. This organization helps ensure the model correctly interprets and addresses each component of your request.
- Set clear requirements: When your request has specific limitations or criteria, state them explicitly (like "Each line should take no more than 5 seconds to say..."). Whether it's budget constraints, time limits, or particular formats, clearly outline these parameters to guide the model's response.
- Clearly describe output: Paint a clear picture of your desired outcome. Describe the specific characteristics or qualities that would make the response exactly what you need, allowing the model to work toward meeting those criteria.
- Majority voting for responses: When evaluating model performance, it is recommended to generate multiple solutions and then use the most frequent results.
- No chain-of-thought prompting: Since these models always reason prior to answering the question, it is not necessary to tell them to "Reason step by step..."
- Math tasks: For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
- Forcing <think>: On rare occasions, R1 1776 tends to bypass the thinking pattern, which can adversely affect the model's performance. In this case, the response will not start with a <think> tag. If you see this problem, try telling the model to start with the <think> tag.
Applications & Use Cases
Reasoning models use-cases
- Analyzing and assessing AI model outputs: Reasoning models excel at evaluating responses from other systems, particularly in data validation scenarios. This becomes especially valuable in critical fields like law, where these models can apply contextual understanding rather than just following rigid validation rules.
- Code analysis and improvement: Reasoning models are great at conducting thorough code reviews and suggesting improvements across large codebases. Their ability to process extensive code makes them particularly valuable for comprehensive review processes.
- Strategic planning and task delegation: These models shine in creating detailed, multi-stage plans and determining the most suitable AI model for each phase based on specific requirements like processing speed or analytical depth needed for the task.
- Complex document analysis and pattern recognition: The models excel at processing and analyzing extensive, unstructured documents such as contract agreements, legal reports, and healthcare documentation. They're particularly good at identifying connections between different documents and making connections.
- Precision information extraction: When dealing with large volumes of unstructured data, these models excel at pinpointing and extracting exactly the relevant information needed to answer specific queries, effectively filtering out noise in search and retrieval processes. This makes them great to use in RAG or LLM augmented internet search use-cases.
- Handling unclear instructions: These models are particularly skilled at working with incomplete or ambiguous information. They can effectively interpret user intent and will proactively seek clarification rather than making assumptions when faced with information gaps.
Looking for production scale? Deploy on a dedicated endpoint
Deploy R1 1776 on a dedicated endpoint with custom hardware configuration, as many instances as you need, and auto-scaling.
