Context Reasoning

Context understanding and reasoning tasks test accurate answers grounded in provided context. This capability is essential for knowledge-base support bots, policy lookup systems, and internal knowledge Q&A applications.

Duration

Input Tokens

Output Tokens

327

Cost

$0.78

Context

Input

In the blogpost about the New OpenAI compatible endpoint with Opper. There is an example where we use deepseek-r1-distill-llama-70b. What is the content (question) passed to the model?

Expected output

What is the capital of France? Please reverse the name before answering.

Model output

In the blogpost about the New OpenAI-compatible endpoint with Opper, the example using `groq/deepseek-r1-distill-llama-70b` passes the following content (question) to the model:

**"What is the capital of France? Please reverse the name before answering."**

This is sent as a user message in the chat completions request, and the model responds by reasoning that the capital is Paris and then reversing it to produce "Sirap".