Skip to main content
Usually, language models have a knowledge cut-off based on the data used for training. With web browsing functionality into Pawa AI, instead of orchestrating searches and tool calls yourself, you can get chat responses enriched with live data directly from the API.
Our Built-in Web Search Tool Example
Web Browsing Example This can be done using the built-in web_search_tool, which you pass as a parameter to your chat request. Unlike other providers, this feature has no extra charges or request limits for browsing.
This can be done using the built-in web_search_tool, which you pass as a parameter to your chat request. Unlike other providers, this feature has no extra charges or request limits for browsing.

Web browsing Models in Pawa AI.

Currently we have one web browsing model:
  • pawa-v1-blaze-20250318: A powerful small language model (SLM) optimized for reasoning, complex generation, multimodal, tools understanding, agentic workflow, and advanced knowledge tasks.

Web Browsing Request Example

curl --request POST \
     --url https://api.pawa-ai.com/v1/chat/request \
     --header "Authorization: Bearer $PAWA_AI_API_KEY" \
     --header 'Content-Type: application/json' \
     --data '{
       "model": "pawa-v1-blaze-20250318",
       "messages": [
         {
           "role": "user",
           "content": [
             {
               "type": "text",
               "text": "What was the score of Yanga SC vs Walliete FC yesterday ?"
             }
           ]
         }
       ],
       "tools": ["web_search_tool"]
     }'
This request allows the model to fetch live information from the web, returning up-to-date and accurate responses directly in the chat.
I