Web search
Ollama announced a new web search API on September 24, 2025. The company said it provides a generous free tier of web searches for individuals, with higher rate limits available through Ollama's cloud. Web search is also included with a free Ollama account, and much higher rate limits are available by upgrading an Ollama subscription.
According to Ollama, the capability can augment models with the latest information from the web to reduce hallucinations and improve accuracy. Web search is offered as a REST API, with deeper tool integrations in Ollama's Python and JavaScript libraries. Ollama said this also enables models such as OpenAI's gpt-oss models to conduct long-running research tasks.
The company also introduced a web fetch API for retrieving individual pages, such as when a user provides a URL in a prompt.
Ollama listed qwen3 and gpt-oss as models with strong tool-use capabilities for multi-turn interactions with users and tools, and listed qwen3:480b-cloud, gpt-oss:120b-cloud, and deepseek-v3.1-cloud as recommended cloud models. It said web_search and web_fetch can return thousands of tokens, recommending increasing model context length to roughly 32,000 tokens for reasonable performance, and noted search agents work best with full context length.
Integrations include a Model Context Protocol server through a Python MCP server, plus Cline, Codex, and Goose. The examples include using Alibaba's Qwen 3 model with 4B parameters for a search agent. To get started, users create an API key from an Ollama account.
Based on reporting from the original publisher. Visit the source for full context and later updates.
Publisher excerpt
A new web search API is now available in Ollama. Ollama provides a generous free tier of web searches for individuals to use, and higher rate limits are available via Ollama’s cloud.