Vani adds Kimi K3.1 Pro Soft-Derisked to chat and API
API pricing is $5 per million input tokens and $7 for output, with an 18-plus confirmation in chat.
API pricing is $5 per million input tokens and $7 for output, with an 18-plus confirmation in chat.
Parallel returns relevant passages and a deeper mode for current questions, with automatic fallback.
The reset restores the current week to 100% once and leaves the regular weekly schedule unchanged.
The free Marketplace extension shows file edits as diffs and runs commands only after approval.
The hosted variant keeps a 1M-token window and is priced at $3 per 1M input and $5 per 1M output tokens.
Prepaid pricing is $3 per 1M input tokens and $5 per 1M output tokens, with a 1M-token window.
The post says derisked models drop the consumer refusal layer while keeping base capability and terms.
Image and video models from chat are now on the API, and AI-made media is marked in file metadata.
Fast GPT replies use 2.5 times more allowance, and Muse Spark 1.3 was later withdrawn.
Those models are on every Vani Chat plan and the API; guests can chat without an account.
The Vani API is live again, and earlier keys and prepaid balances still work.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 2.2K readers · 2.7K views · 397 reads · all time 108K views