Tool Directory
AI agent tools for any LLM
Web search and page reading for any model, plus each maker's own tools, all through Opper. Keep searches in the EU when you need to.
Jina search
Opper's default search engine for models without their own. Search processing stays in the EU.
"engine": "jina"SearchBase
The Swedish open-source search API, on Europe's own Staan index and hosted in the EU.
"engine": "searchbase"Exa search
Exa's search engine built for AI, on any tool-calling model through one tool entry. US-based.
"engine": "exa"Linkup search
Linkup's search for AI apps, running in the US, EU, Canada and APAC, on any tool-calling model.
"engine": "linkup"Google Search grounding
Gemini grounds its answers in Google Search. auto uses it when you call Gemini on generateContent.
native · generateContentxAI web search
Some xAI routes run the model's own search, and auto uses it there.
nativeOpenAI web search
GPT's own search, on the Bing index. auto uses it when you call OpenAI models on the Responses endpoint.
native · ResponsesClaude web search
Claude's own search tool, on the Brave index. auto uses it when you call Claude on the Messages endpoint on a route that has it.
native · MessagesAlibaba web search
Some Alibaba routes run the model's own search, and auto uses it there.
nativeJina Reader
Turn any URL into clean markdown a model can read. Opper's web fetch, running in the EU.
/v3/tools/web/fetchClaude web fetch
Claude fetches and reads pages itself on the Messages endpoint, on Anthropic's own route.
web_fetchGemini URL context
Gemini reads the URLs in your prompt itself, on generateContent.
urlContextMistral OCR 3
Mistral OCR 3, document understanding model with a 74% win rate over OCR 2 on forms, tables, and handwritten text.
/v3/ocrMistral OCR 4.1
Mistral OCR 4.1, the current model behind Mistral's Document AI stack, adding paragraph-level bounding boxes and block-level confidence scores to extracted text.
/v3/ocrOpper Docling OCR
IBM Docling: open-source OCR and document parsing with layout analysis, handling many formats including PDF, images, Office documents, and audio.
/v3/ocrOpenAI code interpreter
GPT models write and run Python in a sandbox, on the Responses endpoint.
code_interpreterGemini code execution
Gemini runs code to work out its answer, on generateContent.
codeExecutionClaude code execution
Claude runs code in Anthropic's sandbox, on Anthropic's own route.
code_executionClaude computer use
Claude drives a desktop through screenshots, clicks and typing in your agent loop.
computer_toolsetClaude bash
Claude runs shell commands in an environment your agent controls.
bashClaude text editor
Claude reads and edits files with its own file-editing tool.
text_editorBGE Reranker v2-m3
BGE-reranker-v2-m3 by BAAI, lightweight 600M cross-encoder reranker built on BGE-m3 for fast multilingual relevance scoring.
/v3/rerankCohere Rerank v3.5
Cohere Rerank v3.5 is a multilingual semantic ranking model that reorders search and RAG results with state-of-the-art precision across 100+ languages and complex enterprise data.
/v3/rerankEmbeddings
Turn text into vectors for search and retrieval, with EU-hosted routes.
26 modelsBrowse by capability
Every tool for one job on one page, with the engines, regions and setup side by side.