Enterprise AI — Command for chat, Embed for search, Rerank for relevance
Connect via PincerAPI
Use our proxy to call Cohere with your PincerAPI key. No separate signup needed.
# Get instructions for Cohere
curl -H "Authorization: Bearer YOUR_PINCER_KEY" \
https://pincerapi.com/api/v1/apis/cohere/instructions
# Call through PincerAPI proxy
curl -H "Authorization: Bearer YOUR_PINCER_KEY" \
"https://pincerapi.com/api/v1/connect/cohere/your/endpoint/here"Direct Setup
Endpoints
/chatGenerate chat responses with Command models
💡 Supports tool_use, documents for RAG, and citation generation
/embedCreate embeddings
💡 input_type affects embedding — use search_document for indexing, search_query for queries
/rerankRerank documents by relevance to a query
💡 Great for re-ordering search results
Related APIs in ai-llm
OpenAI
GPT-4o, o1, DALL·E, Whisper, TTS, embeddings — the leading AI API platform
Anthropic
Claude AI models — Claude 3.5 Sonnet, Claude 3 Opus/Haiku for chat and analysis
Google AI (Gemini)
Gemini models — multimodal AI for text, images, audio, video, and code
Mistral AI
Open-weight AI models — Mistral Large, Small, and specialized coding models
Groq
Ultra-fast LLM inference — LPU-powered, OpenAI-compatible API for Llama, Mixtral, Gemma
Together AI
Open-source model hosting — Llama, Mixtral, SDXL with OpenAI-compatible API