--- title: Kimi K3.1 Pro Soft-Derisked is now on Vani | daily.dev description: Vani has added Kimi K3.1 Pro Soft-Derisked, a version of Moonshot AI's Kimi K3.1 Pro running with Vani's own soft-derisked instructions. It refuses less often... canonical: https://daily.dev/posts/kimi-k3-1-pro-soft-derisked-is-now-on-vani-ozzsgagro twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Kimi K3.1 Pro Soft-Derisked is now on Vani | daily.dev og:description: Vani has added Kimi K3.1 Pro Soft-Derisked, a version of Moonshot AI's Kimi K3.1 Pro running with Vani's own soft-derisked instructions. It refuses less often... og:url: https://daily.dev/posts/kimi-k3-1-pro-soft-derisked-is-now-on-vani-ozzsgagro og:image: https://api.daily.dev/og/posts/ozZsGagRo.png og:image:alt: Kimi K3.1 Pro Soft-Derisked is now on Vani og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Kimi K3.1 Pro Soft-Derisked is now on Vani **[Ahurasense](https://daily.dev/sources/ahurasense)** · 2 min read · 0 upvotes · 0 comments ## Summary Vani has added Kimi K3.1 Pro Soft-Derisked, a version of Moonshot AI's Kimi K3.1 Pro running with Vani's own soft-derisked instructions. It refuses less often than standard Kimi K3.1 Pro but is more conservative than GLM 5.3 Derisked. It's available in Vani Chat on Plus and higher, and via the API as moonshotai/kimi-k3.1-pro-soft-derisked, and it is for adults, with Vani asking users to confirm they are 18 or older. It has 1 million tokens of context, up to 131,072 output tokens, and always thinks first with low, high or max effort. API pricing is $5 per 1M input tokens, $0.50 cached, and $7 output, with Vani's instructions adding about 1,100 input tokens usually billed at the cached rate. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Kimi K3.1 Pro Soft-Derisked on Vani and how does it differ from standard Kimi K3.1 Pro? It is the same Kimi K3.1 Pro model from Moonshot AI running with Vani's own soft-derisked instructions, which make it refuse less often than standard Kimi K3.1 Pro while staying more conservative than GLM 5.3 Derisked. It keeps 1 million tokens of context and up to 131,072 output tokens, and requires users to confirm they are 18 or older in Vani Chat. _Developers evaluating refusal behavior across model variants can compare options like this through daily.dev._ ### What is the API pricing for moonshotai/kimi-k3.1-pro-soft-derisked on Vani? Input tokens cost $5.00 per 1 million, cached input costs $0.50 per 1 million, and output costs $7.00 per 1 million. Vani's soft-derisked instructions add about 1,100 input tokens to each request, and these are usually billed at the cheaper cached rate rather than the full input rate. _Teams budgeting API spend across model variants can track pricing changes like this via daily.dev._ ## Similar posts on daily.dev - [Everyone Read Kimi K3 as a Price War. It Is the Opposite.](https://daily.dev/posts/everyone-read-kimi-k3-as-a-price-war-it-is-the-opposite--xshhpdjyb) · Medium · 3 upvotes · 0 comments - [Moonshot AI’s Kimi K2.7-Code Targets Token Efficiency in Agentic Coding](https://daily.dev/posts/moonshot-ai-s-kimi-k2-7-code-targets-token-efficiency-in-agentic-coding-rpll6qhkm) · DevOps.com · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#moonshot-ai](https://daily.dev/tags/moonshot-ai) [View this post on daily.dev](https://daily.dev/posts/kimi-k3-1-pro-soft-derisked-is-now-on-vani-ozzsgagro) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Kimi K3.1 Pro Soft-Derisked is now on Vani","url":"https://daily.dev/posts/kimi-k3-1-pro-soft-derisked-is-now-on-vani-ozzsgagro","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/kimi-k3-1-pro-soft-derisked-is-now-on-vani-ozzsgagro"},"datePublished":"2026-10-27T16:01:43.008Z","dateModified":"2026-10-27T16:05:17.826Z","description":"Vani has added Kimi K3.1 Pro Soft-Derisked, a version of Moonshot AI's Kimi K3.1 Pro running with Vani's own soft-derisked instructions. It refuses less often...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/66f84026620cfaf6eb07adf421d1c0b6?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/66f84026620cfaf6eb07adf421d1c0b6?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ahurasense","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Ahurasense","logo":"https://media.daily.dev/image/upload/s--WNYcnrr7--/f_auto/v1790970263/squads/b4b1b632-59d4-4ff2-95a4-bf38f90e102d?_a=BAMAMicg0","url":"https://daily.dev/squads/ahurasense"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/kimi-k3-1-pro-soft-derisked-is-now-on-vani-ozzsgagro","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,moonshot-ai","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ahurasense","item":"https://daily.dev/squads/ahurasense"},{"@type":"ListItem","position":3,"name":"Kimi K3.1 Pro Soft-Derisked is now on Vani"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/kimi-k3-1-pro-soft-derisked-is-now-on-vani-ozzsgagro#faq","mainEntity":[{"@type":"Question","name":"What is Kimi K3.1 Pro Soft-Derisked on Vani and how does it differ from standard Kimi K3.1 Pro?","acceptedAnswer":{"@type":"Answer","text":"It is the same Kimi K3.1 Pro model from Moonshot AI running with Vani's own soft-derisked instructions, which make it refuse less often than standard Kimi K3.1 Pro while staying more conservative than GLM 5.3 Derisked. It keeps 1 million tokens of context and up to 131,072 output tokens, and requires users to confirm they are 18 or older in Vani Chat. Developers evaluating refusal behavior across model variants can compare options like this through daily.dev."}},{"@type":"Question","name":"What is the API pricing for moonshotai/kimi-k3.1-pro-soft-derisked on Vani?","acceptedAnswer":{"@type":"Answer","text":"Input tokens cost $5.00 per 1 million, cached input costs $0.50 per 1 million, and output costs $7.00 per 1 million. Vani's soft-derisked instructions add about 1,100 input tokens to each request, and these are usually billed at the cheaper cached rate rather than the full input rate. Teams budgeting API spend across model variants can track pricing changes like this via daily.dev."}}]} ```