Voyage AI (direct)

Direct Voyage AI API calls (voyageai SDK or raw HTTP, no framework). Base URL is https://api.voyageai.com/v1; the vendor exposes POST /embeddings and POST /rerank — embeddings and rerank only, no chat/completion endpoint. No OpenAI-compatible route is published. Voyage has no admin/billing API (usage is dashboard-only), so spend is only capturable via this customer-side OTLP push. Token accounting is input-only: an embedding or rerank call has no completion, so there is no meaningful output_tokens metric — one that could only ever read zero would be worse than omitting it. input_tokens and total_tokens (Voyage's usage object reports both, and they are equal for embedding calls) are what this connector reports instead. No telara-observability provider wrapper exists for Voyage today (the package's optional-dependencies only cover langchain/langgraph/crewai/ autogen/llamaindex/openai-agents/openai/anthropic/azure-openai) — spans must come from the customer's own OTel instrumentation around the Voyage SDK call. Spans should be tagged telara.span.kind=provider so the cost rollup excludes them when an active framework adapter already covers the same call (double-count guard).