Vercel

Any MCP client can now ask to connect to . You still log in and approve each connection, but the client no longer has to be reviewed by Vercel first. Previously, Vercel reviewed and allowlisted each client and its redirect URIs by hand, and anything not on the list was rejected.Vercel MCP To connect, a client publishes a Client ID Metadata Document (CIMD), a JSON file on its own domain that describes it, and uses that file's HTTPS URL as its OAuth . This follows the MCP authorization spec, which now recommends CIMD over Dynamic Client Registration.client_id Because Vercel hasn't reviewed thes...

can now show your deployments as an interactive card inside ChatGPT and other chat clients that support .Vercel MCPMCP Apps The card shows live deployment status, build logs, and source and commit details, with a Visit button once the deployment URL is ready. You can send logs into the chat to debug with the model, or open the fullscreen view to read them beneath the card. For repositories linked to multiple projects, a project list lets you switch between them. The card is Vercel MCP's first MCP App, built on the MCP Apps extension. Clients without app support receive the deployment state, p...

is now available on AI Gateway. This model combines native visual understanding with coding and multi-step tool use for agents working across complex codebases and full-project builds.LongCat 2.5 from Meituan improvements in visual programming, creative design, and 3D tasks, alongside longer agent workflows that carry engineering work from planning through execution. The model supports text and image inputs with a 1M-token context window for code, documents, and extended task histories.Meituan highlights Use as the model name:meituan/longcat-2.5 To use it in Claude Code, Codex, Cursor, and mo...

is now available on , free until November 3, 2026.Ling 3.1 Flash 1019 from InclusionAIAI Gateway The updated model is designed for coding, multi-step reasoning, and agents that use tools. Its 1M-token context window supports workflows involving long documents, code, and extended task histories. Use as the model name:inclusionai/ling-3.1-flash-1019 Free requests still appear in your spend dashboard with a full request trace, they just cost nothing. On November 3, requests will begin charging at the published rate. To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI...

, the open-source AI penetration testing tool, can now run on any of the 400+ models on Vercel .StrixAI Gateway Strix can reach models from Anthropic, OpenAI, Kimi, GLM, Deepseek, and others through a single API with no markup, removing the need to sign up for multiple providers. Usage and cost are tracked across all models in AI Gateway. Strix selects the Gateway through , where the model is the standard AI Gateway ID behind a prefix:STRIX_LLM / vercel_ai_gateway/ See to configure it and get started today.Strix's AI Gateway setup guide Read more

You can now log or block requests from AI crawlers and AI assistants separately with the AI Bots managed ruleset in .Vercel Firewall For example, you can block AI crawlers while allowing AI assistants to retrieve your content to answer users’ questions. Vercel updates the rules as new bots are added. To configure these controls, open your project’s . Under , enable and select the gear icon beside it. Set an action for AI crawlers and AI assistants, then review and publish your changes.Security > Firewall > RulesBot ManagementAI Bots You can also modify these rule settings using the Vercel CLI...

now uses updated weights on , with lower pricing for input, cached input, and output tokens.Mistral Large 4 from MistralAI Gateway According to , the updated weights improve agentic coding and defensive cybersecurity, with greater token efficiency on coding tasks. The release also improves spreadsheet creation and editing, web research, and resistance to prompt injection.Mistral’s release announcement If you were already using via AI Gateway, there is no need to change your model to start using the updated version. The existing model ID string uses the new model with updated weights and prici...

Today, we are introducing on .Virtual ModelsAI Gateway Virtual Models are an abstraction of the model string and configurations your apps and developers use. With a single virtual model ID, you can change and update models, configure fallbacks and priority, and enforce Zero Data Retention centrally. The virtual model configuration applies wherever the ID is used. Assign a virtual model ID to an agent task, and pass it as the model string wherever that task is called. You can then change the model and settings behind the virtual model ID in AI Gateway, and your apps and agents will pick up the...

are now available on . Virtual modelsAI Gateway A virtual model is a saved configuration that tells AI Gateway which model and settings to use. Your apps and agents call it with a custom model ID, such as . You can change the model or settings centrally in AI Gateway without redeploying your apps or reconfiguring your agents.vmc/coding-agent Use virtual models to: To create a virtual model, open the and click . Enter a slug, choose the underlying model, configure the settings you want requests to use, and save.Virtual Models pageCreate Virtual Model Or create one with the :Vercel CLI To use a...

from Particle AI is now available on . It is post-trained on DeepSeek V4.1 Flash, with a focus on completing software engineering tasks using fewer tokens. Particle describes the gains as shorter reasoning, fewer rounds of trial and repair, and more focused exploration.Particle-1AI Gateway Use it for debugging, planning code changes, and breaking down multi-step engineering problems. Particle-1 has a 1M-token context window for working with code and extended task histories. Set in your environment. Use as the model name:AI_GATEWAY_API_KEYparticle/particle-1 To use it in Claude Code, Codex, Cu...

You can now query AI traffic in to understand how AI bots are accessing your site.Vercel Observability AI traffic insights show: To view AI traffic insights, open in the Vercel dashboard.Observability > AI Traffic You and your agents can also query these metrics with in the . CLI queries require Observability Plus.vercel metricsVercel CLI type: embedded-entry-inline id: 6E78NBZeL598kMHZ7c4zyk Learn more in the .AI traffic documentation Read more how many requests each bot makesRequests by verified AI bot: pages most frequently requested by AI crawlers for indexing or model trainingMost-crawle...

Vercel and are partnering to bring 14 ElevenLabs models to . To celebrate the launch, all ElevenLabs models are 50% off on AI Gateway for the first 14 days, through November 9th.ElevenLabsAI Gateway AI Gateway supports six different types of ElevenLabs audio models: All of these audio models are accessible through a single gateway API key. Your app or agent can transcribe what a user says, reason over it with your choice of hundreds of models, then answer in an ElevenLabs voice. You can also create soundtracks with generated music and sound effects. Every request lands in the same usage, cost...

, Scale AI's framework for testing agents against tasks and scoring their results, now runs on . The Vercel provider ships in AgentEnv 0.9.1334 and later, and runs the agent and its task environment in separate Sandboxes.AgentEnvVercel Sandbox Try the to run an evaluation on Vercel Sandbox and inspect the task’s score and the agent’s recorded actions. After completing the , run this command from the cloned repository. It uses your existing Vercel CLI login:AgentEnv examplesetup guide Replace with your Vercel team slug and with an existing project name.YOUR_TEAMYOUR_PROJECT Learn more in the ....

now includes , a tool for sending bug reports, friction reports, and feature requests directly to the Vercel team from your agent or harness.Vercel MCPsubmit_feedback Ask your agent to give feedback in plain language: Your assistant can attach structured context that describes the task, the expected behavior, and what went wrong: The tool requires sign-in, and it sends feedback only when you ask your agent to share it. Connect your agent to Vercel MCP and read the to get started.submit_feedback documentation Read more Send Vercel feedback that the deployment error didn't explain which environ...

from is now available on , along with , a faster version for interactive use.Kimi K3.1 ProMoonshot AIAI GatewayKimi K3.1 Pro Highspeed K3.1 Pro is the first model in Moonshot's K3.1 series. It builds on with improvements in coding, 3D modeling, financial analysis, and agentic tasks, and keeps the 1M-token context window and image input.Kimi K3 For coding, K3.1 Pro handles work ranging from small fixes in an existing codebase to building a full project, including long agent runs with many steps. It builds front-end pages and interactive scenes with stronger typography and animation than earlie...

and from Baseten are now available for free on AI Gateway for one week. Free access is available through October 27. These decision models classify text, route requests, and score content against criteria you define.Mammoth-1Elephant-1 Mammoth-1 is the larger, 27B model, while Elephant-1 is a smaller, 9B option. Mammoth-1 is #1 on the Jev Decision Index and Elephant-1 is tied for #1 on the Artificial Analysis Decision Index. Both support a 16k-token context window and return choices, probabilities, and scores. Ask several questions about the same input in one request: select a support team wi...

now includes DeepSeek V4.1 Flash, alongside Kimi K3 and GLM 5.3, each accessed through its preferred provider, with more models to come. The DeepSeek model uses the latest weights (1017).Token Pass Token Pass is a $30/month subscription on Pro teams that grants $80 in monthly credit and runs through . Use it with any coding agent such as , , , etc. or build your own with the AI SDK, with Zero Data Retention enabled by default.AI GatewayfxPiClineCommand Code Add DeepSeek V4.1 Flash from the in your team's AI Gateway dashboard, or read the for setup.Token Pass pageToken Pass documentation Read ...

is now available on AI Gateway with 50% off launch pricing. Inception reports strong results across a range of benchmarks, with generation speeds above 1,000 tokens per second.Mercury 3 from Inception Mercury 3 uses diffusion to generate text through parallel refinement. It brings improved reasoning to latency-sensitive workloads such as browser agents, real-time search, interactive education, and customer support. A 1M-token context window gives those applications room for long documents and extended conversation histories. Set in your environment. Use as the model name:AI_GATEWAY_API_KEYinc...

from is now available on for free until Oct 22.MiniMax M3.1 FlashMiniMaxAI Gateway MiniMax M3.1 Flash is an open-weight multimodal model for coding and agentic work, with a 1M-token context window for long documents and multi-step agent sessions. Compared with earlier MiniMax models, M3.1 Flash improves on complex agentic tasks, coding, and cybersecurity. On the agent side, that covers multi-step business processes and computer use that carries a task from one application to the next. For coding, MiniMax reports its best results on application development, particularly frontend interactions, ...

now have a that groups requests into sessions and shows how session affinity routed each one. Each row shows the or app that ran the session, such as Claude Code, Codex, or Cursor, along with its cost, models, providers, and how much of its input was cached across every turn.AI Gateway logsSessions viewcoding agent Open a session to see its cache hit rate, duration, and path. The path lists each turn with its model and timing, and names the provider serving the session along with any earlier ones. sends each turn to the provider that served the one before it, so the provider already has most ...

is now available on .DeepSeek V4.1 Flash 1017AI Gateway DeepSeek V4.1 Flash 1017 is a minor update to that improves reasoning, coding, agentic tasks, and image understanding.DeepSeek V4.1 Flash The coding gains show up in terminal work and in building and editing whole repositories, and the agentic gains in multi-step automation. With images, the model reads charts and handles visual reasoning more accurately when it can call tools. DeepSeek V4.1 Flash 1017 also finishes tasks faster and with shorter outputs than the previous snapshot, so agent runs tend to take less time and use fewer output...

is now available on AI Gateway. The visual reasoning model accepts images and video to follow objects through motion, interpret spatial relationships, and connect an action to its physical consequences.Glimpse from Elorian Glimpse can return to visual evidence as it works: zooming into a detail, revisiting a short interval of video, or tracking the same feature across frames. This allows the model to support use cases like scientific chart analysis, video captioning, visual counting, and robotics data annotation. Some examples include checking a train's motion to determine whether it is slowi...

and are now available on . Both are multimodal for classifying content, routing requests, and scoring text, structured records, and images.Perplexity Decider V1.2 27BDecider Flash V1.2 4BAI Gatewaydecision models The models answer typed questions with probabilities. Boolean questions return the likelihood of yes, Choice questions select from categories you define, and Score questions assess content against an ordered rubric. Your application can use those results to route a support ticket, flag a damaged product, or send an uncertain decision for human review. Multiple questions can share the...

, previously available in stealth as , is now available on . Beam is free to use for a limited time during the launch period when serviced by Reflection AI.Beam from Reflection AIAI Gatewaystealth/cat-jam Beam is an low latency US open-weight reasoning model for coding and agentic tasks, with . Beam supports and , with a 1M-token context window for code, documents, and conversation history. Reasoning effort is adjustable. Beam is designed for speed, activating only 23B of its 501B parameters per token and avoiding tokens a task doesn't need, so it tends to reach answers sooner than larger ope...

is now available on AI Gateway. It is a multimodal decision model for classification, routing, and scoring across text and images, including visual defect inspection and checking damage claims against customer photos.d1-ultra from Liquid AI Rather than generating text, d1-ultra returns structured answers with probabilities. Ask a Boolean question to get the probability of a yes/no answer, use Choice to select among named categories, or use Score to rate an ordered scale. You can ask multiple questions about the same input in one request and use the probabilities to decide when to automate an ...

is now available on AI Gateway. The open-weight reasoning model is designed for coding and agentic workflows, including multi-file refactoring, debugging, and understanding large codebases.Muse Spark Open from Meta Muse Spark Open supports text and image input with a 1M-token context window, allowing agents to work with code and screenshots in the same request. It is available with and no training, without creating separate provider accounts.ZDR Use as the model name across all API formats and coding agents. The model is available across the , the OpenAI-compatible and APIs, the , and connect...

is now available on as a stealth model, free to use during the stealth period.Cat JamAI Gateway Cat Jam is a reasoning model for coding and agentic tasks, with low-latency inference. It supports , so agents can connect it to your own tools, and that follow a JSON schema you supply. Responses include the model's reasoning text alongside the answer. Cat Jam takes text input only. Cat Jam supports , , , , and reasoning efforts.function callingstructured outputslowmediumhighxhighmax (ZDR) is not available for this model. Prompts may be retained for safety reasons.Zero Data Retention Cat Jam works...

now supports MCP Events in public beta, allowing your apps and agents to subscribe to webhook events from compatible MCP servers. Build agents for tasks like summarizing new messages, reviewing newly created issues, or responding to document feedback.Vercel Connect Connect creates subscriptions on the MCP server and renews them automatically as needed, verifying the server’s webhooks and forwarding events to your application using authenticated delivery. You can use the Connect SDK to subscribe to MCP events: At your delivery endpoint, use the SDK to verify that each delivery came from Connec...

is now available on .Jev 1.14 from TypeSafe AIAI Gateway Jev is a for software. You pass it state and a set of questions, and it returns typed Choice, Score, and Boolean answers with probabilities instead of free-form text. It answers every question in one request, in parallel, for classification, routing, scoring, and automated verification.decision model Jev 1.14 accepts images as part of the state, and has an experimental long-context mode for documents, logs, or conversation histories that are too long for a standard request. Use as the model name.typesafe-ai/jev-1.14.0 Pass an image as a...

is now available for free on , served by NVIDIA.Nemotron 3.5 LightningAI Gateway The open-weight reasoning and chat model supports long-running agents, subagents, chatbots, and retrieval-augmented generation (RAG). It has a 1 million-token context window, supports tool calling and structured outputs, and uses 3 billion of its 30 billion parameters per token. Note: The provider may retain prompts for model improvement. Use as the model ID:nvidia/nemotron-3.5-lightning-free To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select in the agent. ...

, Fish Audio’s text-to-speech model, is now available in preview on and 80% off through November 12.Drama 3AI Gateway Use it for voiceovers, character dialogue, and audio storytelling, with: Use with the :fish-audio/drama-3AI SDK Choose a voice from and use its ID as . For authentication and setup, follow the .Fish Audio’s voice libraryspeech quickstartvoice Try Drama 3 in the .model playground Read more Set emotion and pacing with instructions in square brackets, add sounds and pauses, or apply tags such as and to selected words.Voice controls: Write instructions in a different language from...

Microsoft’s and are now available on . Generate images from text or edit existing images with one AI Gateway API key, without a Microsoft account.MAI-Image-2.6MAI-Image-2.6-FlashAI Gateway Both models support photorealistic images, text rendering, and targeted edits to products, portraits, and layouts. Use up to five reference images to guide edits or combine subjects, with output sizes up to 1536 × 1536 pixels. To generate an image, use either model ID with a text prompt: To edit an image, provide a reference image and describe what to change: Try or in the playground, or read the . MAI-Imag...

from is now available on .Gemini 4 ArgonGoogleAI Gateway Gemini 4 Argon is built for coding, agentic work, and complex reasoning. It has a 1M token context window, accepts text, image, PDF, and video input, and supports tool calling. On coding tasks, Gemini 4 Argon builds features, fixes bugs, and researches unfamiliar codebases, carrying longer tasks through multiple steps. The model also reads dense diagrams, spreadsheets, layout-heavy documents, and video, which suits tasks like a financial analysis spread across several spreadsheet tabs. Beyond code, it handles work in finance, health, an...

is now available on AI Gateway. The model is designed for coding, long-running agents, and computer use. It can plan multi-step tasks, delegate work to sub-agents, and recover from errors as work progresses.Muse Wonder from Meta Muse Wonder has a 1M-token context window and supports text, image, and PDF input, tool calling, and structured output. Agents can work with code, screenshots, and documents in the same workflow. You can access the model through AI Gateway with one API key, without creating a separate Meta account. Set in your environment, then use as the model name:AI_GATEWAY_API_KEY...

Rillet on Vercel Standardizing every internal agent on eve Running customer requests through agents, end to end Using AI Gateway to give every builder every model Managing builder access through Enterprise Managed Users Tripled shipping rate in three months with eve agents deployed on Vercel Two-person team closed 800+ Linear tickets in its first 4 months Builder access via Enterprise Managed Users, SSO, and Directory Sync Ships customer-requested changes to production in as little as two hours Gives every builder access to models through AI Gateway is an AI-native enterprise resource plannin...

is now available on . It answers typed questions about text with probabilities, choices, and scores. It can be used to classify support requests, select the next step in a workflow, or assess an AI response against a rubric.Decision-1 from MicrosoftAI Gateway The model can answer yes/no questions, choose among named categories, or score an input against an ordered set of criteria. Multiple questions can share the same input in one request. Choice and score answers include probabilities for each option, so your application can decide when to act or send an uncertain result for review. Call Dec...

is now available on .Liquid d1AI Gateway d1 is a that evaluates shared state against typed questions for classification, routing, and scoring. It returns structured answers with probabilities without generating text tokens. decision model d1 also has vision support: the model can answer typed questions about images for visual classification, inspection, and scoring. Use through the , the , or the . These examples ask whether a support agent issued a refund:liquid/d1AI SDK decision APIOpenAI-compatible Decisions APITypeSafe-compatible API This example reads a local PNG named and asks which col...

from xAI is now available on AI Gateway. This lightweight model turns text prompts and images into video with native audio.Grok Imagine Video 1.5 Lite The model produces clips from 1 to 15 seconds long in 480p, 720p, and 1080p. Seven aspect ratios cover widescreen, square, and portrait formats, so you can create horizontal scenes or vertical videos from the same generation workflow. To start generating videos, set the model to in the or in the . Chain an image model with Grok Imagine Video 1.5 Lite to create a still and animate it in one flow.spacexai/grok-imagine-video-1.5-liteAI SDKAI CLI Y...

, StepFun's flagship model, is now available on . It's built for agentic coding, professional knowledge work, and financial analysis, from building apps and debugging code to research and analytical reports.Step 5 PreviewAI Gateway Step 5 Preview supports text and image input with a 1M-token context window, allowing you to work with large codebases, a stack of documents, or screenshots and charts in a single request. Use as the model name:stepfun/step-5-preview For other coding agents such as Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select in the...