--- title: DeepSeek V4 Flash now runs updated weights on AI Gateway description: DeepSeek V4 Flash on Vercel's AI Gateway has been updated with new model weights, boosting its Terminal-Bench score from 56.9 to 82.7 — a 25.8-point... canonical: https://daily.dev/posts/deepseek-v4-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: DeepSeek V4 Flash now runs updated weights on AI Gateway | daily.dev og:description: DeepSeek V4 Flash on Vercel's AI Gateway has been updated with new model weights, boosting its Terminal-Bench score from 56.9 to 82.7 — a 25.8-point... og:url: https://daily.dev/posts/deepseek-v4-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore og:image: https://api.daily.dev/og/posts/9EQHPAoRe.png og:image:alt: DeepSeek V4 Flash 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 Flash now runs updated weights on AI Gateway **[Vercel](https://daily.dev/sources/vercel)** · 2 min read · 2 upvotes · 0 comments ## Summary DeepSeek V4 Flash on Vercel's AI Gateway has been updated with new model weights, boosting its Terminal-Bench score from 56.9 to 82.7 — a 25.8-point improvement reflecting stronger agentic capabilities. Requests using the existing model ID `deepseek/deepseek-v4-flash` automatically pick up the new weights with no code changes required. Currently only DeepSeek serves the updated weights; other providers including Zero Data Retention options are coming next week. The model can be used via the AI SDK and is also configurable for coding agents through the `vercel ai-gateway coding-agents setup` command. AI Gateway passes through provider pricing with no markup or platform fee. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Does upgrading to the new DeepSeek V4 Flash weights on Vercel AI Gateway require changing my model ID or code? No, requests to the deepseek/deepseek-v4-flash model ID automatically pick up the new weights with no change to the model ID or code required. The update improved the model's Terminal-Bench score from 56.9 to 82.7, reflecting notably stronger agentic capabilities, and DeepSeek is currently the only provider serving these updated weights. _daily.dev keeps developers tracking model upgrades like this DeepSeek weight swap without breaking their pipelines._ ### How much did DeepSeek V4 Flash's agentic performance improve on Terminal-Bench with the new weights? DeepSeek V4 Flash's Terminal-Bench score jumped 25.8 points, from 56.9 in the April preview to 82.7 with the updated weights served through Vercel AI Gateway. This reflects a substantial gain in agentic capability, relevant for tasks like fixing failing tests or opening pull requests autonomously. _Developers comparing coding agent models can follow benchmark shifts like this one on daily.dev._ ### How do I connect DeepSeek V4 Flash to a coding agent through Vercel AI Gateway? Run the vercel ai-gateway coding-agents setup command to connect agents to AI Gateway, then select deepseek/deepseek-v4-flash in the agent's model configuration. AI Gateway routes requests to providers serving the updated weights by default, with no markup on provider pricing and no platform fee on inference, including Bring Your Own Key requests. _daily.dev helps developers wiring up coding agents stay current on gateway setup steps like this._ ## 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 API Docs](https://daily.dev/posts/deepseek-api-docs-mqussratb) · Hacker News · 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 - [Why not use DeepSeek Flash for everything? · Los Techies](https://daily.dev/posts/why-not-use-deepseek-flash-for-everything-los-techies-sq77ike6a) · LosTechies · 1 upvotes · 1 comments --- Tags: [#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), [#ai-sdk](https://daily.dev/tags/ai-sdk) [View this post on daily.dev](https://daily.dev/posts/deepseek-v4-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore) ```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 Flash now runs updated weights on AI Gateway","url":"https://daily.dev/posts/deepseek-v4-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/deepseek-v4-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore"},"datePublished":"2026-07-31T17:22:57.318Z","dateModified":"2026-09-14T07:04:43.065Z","description":"DeepSeek V4 Flash on Vercel's AI Gateway has been updated with new model weights, boosting its Terminal-Bench score from 56.9 to 82.7 — a 25.8-point...","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-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,vercel,deepseek,ai-gateway,ai-sdk","timeRequired":"PT2M"} {"@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 Flash now runs updated weights on AI Gateway"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/deepseek-v4-flash-now-runs-updated-weights-on-ai-gateway-9eqhpaore#faq","mainEntity":[{"@type":"Question","name":"Does upgrading to the new DeepSeek V4 Flash weights on Vercel AI Gateway require changing my model ID or code?","acceptedAnswer":{"@type":"Answer","text":"No, requests to the deepseek/deepseek-v4-flash model ID automatically pick up the new weights with no change to the model ID or code required. The update improved the model's Terminal-Bench score from 56.9 to 82.7, reflecting notably stronger agentic capabilities, and DeepSeek is currently the only provider serving these updated weights. daily.dev keeps developers tracking model upgrades like this DeepSeek weight swap without breaking their pipelines."}},{"@type":"Question","name":"How much did DeepSeek V4 Flash's agentic performance improve on Terminal-Bench with the new weights?","acceptedAnswer":{"@type":"Answer","text":"DeepSeek V4 Flash's Terminal-Bench score jumped 25.8 points, from 56.9 in the April preview to 82.7 with the updated weights served through Vercel AI Gateway. This reflects a substantial gain in agentic capability, relevant for tasks like fixing failing tests or opening pull requests autonomously. Developers comparing coding agent models can follow benchmark shifts like this one on daily.dev."}},{"@type":"Question","name":"How do I connect DeepSeek V4 Flash to a coding agent through Vercel AI Gateway?","acceptedAnswer":{"@type":"Answer","text":"Run the vercel ai-gateway coding-agents setup command to connect agents to AI Gateway, then select deepseek/deepseek-v4-flash in the agent's model configuration. AI Gateway routes requests to providers serving the updated weights by default, with no markup on provider pricing and no platform fee on inference, including Bring Your Own Key requests. daily.dev helps developers wiring up coding agents stay current on gateway setup steps like this."}}]} ```