--- title: DeepSeek V4 Pro now runs updated weights on AI Gateway description: DeepSeek V4 Pro on Vercel's AI Gateway now serves updated model weights by default when calling deepseek/deepseek-v4-pro, requiring no code changes. Developers... canonical: https://daily.dev/posts/deepseek-v4-pro-now-runs-updated-weights-on-ai-gateway-tcnytkoiz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: DeepSeek V4 Pro now runs updated weights on AI Gateway | daily.dev og:description: DeepSeek V4 Pro on Vercel's AI Gateway now serves updated model weights by default when calling deepseek/deepseek-v4-pro, requiring no code changes. Developers... og:url: https://daily.dev/posts/deepseek-v4-pro-now-runs-updated-weights-on-ai-gateway-tcnytkoiz og:image: https://api.daily.dev/og/posts/tcnyTkoiZ.png og:image:alt: DeepSeek V4 Pro now runs updated weights on AI Gateway 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. # DeepSeek V4 Pro now runs updated weights on AI Gateway **[Vercel](https://daily.dev/sources/vercel)** · 1 min read · 2 upvotes · 0 comments ## Summary DeepSeek V4 Pro on Vercel's AI Gateway now serves updated model weights by default when calling deepseek/deepseek-v4-pro, requiring no code changes. Developers who want to pin the exact version can specify the dated model ID deepseek/deepseek-v4-pro-0813 in the AI SDK. The same dated ID can be selected when connecting coding agents to AI Gateway via the vercel ai-gateway coding-agents setup command. AI Gateway continues to charge no markup on provider pricing, including for Bring Your Own Key requests. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I pin the previous version of DeepSeek V4 Pro on Vercel AI Gateway instead of getting the updated weights automatically? Set the model to the dated model ID deepseek/deepseek-v4-pro-0813 in the AI SDK instead of the default deepseek/deepseek-v4-pro alias, which now routes to updated weights automatically. The dated ID pins the specific version so requests continue behaving the same even as the default alias updates in the future. _Track model version changes like this DeepSeek update on daily.dev before they affect production requests._ ### How do I connect a coding agent to DeepSeek V4 Pro through Vercel AI Gateway? Run the command vercel ai-gateway coding-agents setup to connect an agent to AI Gateway, then select deepseek/deepseek-v4-pro-0813 in the agent's model configuration to use the updated weights. This lets a coding agent route requests, such as fixing failing tests and opening a pull request, through the gateway. _Developers wiring coding agents to new models follow updates like this on daily.dev._ ### Does Vercel AI Gateway charge extra fees on top of provider pricing for models like DeepSeek? No, AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including for Bring Your Own Key (BYOK) requests. This applies to models such as DeepSeek V4 Pro routed through the gateway. _Compare gateway pricing and model options on daily.dev when choosing how to route LLM inference._ ## Similar posts on daily.dev - [Deepseek V4 on AI Gateway](https://daily.dev/posts/deepseek-v4-on-ai-gateway-nas1vjnsv) · Vercel · 0 upvotes · 0 comments - [DeepSeek models now available via Azure on AI Gateway](https://daily.dev/posts/deepseek-models-now-available-via-azure-on-ai-gateway-9vh5c60c3) · Vercel · 0 upvotes · 0 comments - [DeepSeek’s steep V4-Pro price cut escalates AI pricing war](https://daily.dev/posts/deepseek-s-steep-v4-pro-price-cut-escalates-ai-pricing-war-ssyvrmhnt) · InfoWorld · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#vercel](https://daily.dev/tags/vercel), [#deepseek](https://daily.dev/tags/deepseek), [#ai-gateway](https://daily.dev/tags/ai-gateway) [View this post on daily.dev](https://daily.dev/posts/deepseek-v4-pro-now-runs-updated-weights-on-ai-gateway-tcnytkoiz) ```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":"DeepSeek V4 Pro now runs updated weights on AI Gateway","url":"https://daily.dev/posts/deepseek-v4-pro-now-runs-updated-weights-on-ai-gateway-tcnytkoiz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/deepseek-v4-pro-now-runs-updated-weights-on-ai-gateway-tcnytkoiz"},"datePublished":"2026-08-12T16:25:13.239Z","dateModified":"2026-09-14T08:56:44.298Z","description":"DeepSeek V4 Pro on Vercel's AI Gateway now serves updated model weights by default when calling deepseek/deepseek-v4-pro, requiring no code changes. Developers...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/56af0a97832ec561ef20d3587c0634e8?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/56af0a97832ec561ef20d3587c0634e8?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Vercel","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":"Vercel","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/04cca7235cf84db092f24b7ba427b3e1","url":"https://daily.dev/sources/vercel"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/deepseek-v4-pro-now-runs-updated-weights-on-ai-gateway-tcnytkoiz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,vercel,deepseek,ai-gateway","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Vercel","item":"https://daily.dev/sources/vercel"},{"@type":"ListItem","position":3,"name":"DeepSeek V4 Pro now runs updated weights on AI Gateway"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/deepseek-v4-pro-now-runs-updated-weights-on-ai-gateway-tcnytkoiz#faq","mainEntity":[{"@type":"Question","name":"How do I pin the previous version of DeepSeek V4 Pro on Vercel AI Gateway instead of getting the updated weights automatically?","acceptedAnswer":{"@type":"Answer","text":"Set the model to the dated model ID deepseek/deepseek-v4-pro-0813 in the AI SDK instead of the default deepseek/deepseek-v4-pro alias, which now routes to updated weights automatically. The dated ID pins the specific version so requests continue behaving the same even as the default alias updates in the future. Track model version changes like this DeepSeek update on daily.dev before they affect production requests."}},{"@type":"Question","name":"How do I connect a coding agent to DeepSeek V4 Pro through Vercel AI Gateway?","acceptedAnswer":{"@type":"Answer","text":"Run the command vercel ai-gateway coding-agents setup to connect an agent to AI Gateway, then select deepseek/deepseek-v4-pro-0813 in the agent's model configuration to use the updated weights. This lets a coding agent route requests, such as fixing failing tests and opening a pull request, through the gateway. Developers wiring coding agents to new models follow updates like this on daily.dev."}},{"@type":"Question","name":"Does Vercel AI Gateway charge extra fees on top of provider pricing for models like DeepSeek?","acceptedAnswer":{"@type":"Answer","text":"No, AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including for Bring Your Own Key (BYOK) requests. This applies to models such as DeepSeek V4 Pro routed through the gateway. Compare gateway pricing and model options on daily.dev when choosing how to route LLM inference."}}]} ```