Vercel AI Gateway

Overview

What kind of product Category ?

Managed gateway Not verified

Marketplaces resell many providers behind one key. Gateways add governance on top. Open-source projects you run yourself. Cloud platforms are hyperscaler surfaces. Inference providers host models on their own hardware.

Who runs it Deployment model ?

Managed only Verified 2 days ago

Managed means the vendor operates it. Self-host means you run it on your own infrastructure. Both means you can choose.

Licence Licence ?

Proprietary Verified 2 days ago

Proprietary products cannot be inspected or forked. Open licences such as MIT and Apache-2.0 let you audit, modify, and run the code without permission.

Company Company ?

Vercel Not verified

The organisation that maintains the product.

Who you would be signing with Vendor status ?

Independent company Not verified

Whether the product is still an independent company, has been acquired, is a large cloud vendor’s product line, is run by a software foundation, or has been put into maintenance mode. Maintenance mode means bug fixes and security patches only — no new features.

Last shipped an update Latest release ?

2026-08-28 Not verified

The date of the most recent release or version tag. A product that has not shipped in a year is a different risk from one that shipped last week, regardless of what its marketing site says.

GitHub stars GitHub stars ?

Not published Not verified

A rough proxy for community size on open-source projects. Not a quality measure.

Cost

Markup on model prices Token markup ?

None Verified 2 days ago

How much the product adds on top of what the underlying model provider charges. Zero means you pay the same per-token price you would pay the model provider directly.

Fee to add funds Credit purchase fee ?

None Verified 2 days ago

A percentage charged when you top up your balance, separate from token prices. It is easy to miss because it does not appear on the per-token price list.

Monthly cost per person Seat fee ?

$20/user/mo Verified 2 days ago

A recurring per-user platform charge that applies regardless of how much you use the models.

Can use your own provider accounts BYOK supported ?

Yes Verified 2 days ago

Bring Your Own Key: you keep direct contracts with OpenAI, Anthropic and others, and the gateway only routes traffic. This preserves negotiated rates and committed-spend discounts.

Cost of using your own accounts BYOK terms ?

No markup or fee on BYOK, but BYOK requires purchased AI Gateway Credits (paid tier); failed BYOK requests fall back to Vercel system credentials and are billed against credits, and BYOK spend is not covered by budgets. Verified 2 days ago

What the product charges to route traffic through your own provider keys.

Free tier Free tier ?

Every team gets free AI Gateway credits on a subset of models with lower per-model rate limits; the amount is not published. Pro plans include $20 of credit across resources. Verified 2 days ago

What you can do without paying, useful for evaluation.

Enterprise plan from Enterprise plan from ?

Not published Not verified

Annual entry price for the enterprise tier, where one is published or credibly reported.

Cost to run it yourself Self-host cost ?

Not published Not verified

What self-hosting actually costs once you account for infrastructure and any paid tier.

How the vendor makes money Pricing model ?

Percentage on tokens or top-ups Not verified

The shape of the vendor’s bill: does the routing layer charge a percentage on top of tokens, a flat monthly fee, both, neither (because inference is the product), or nothing at all (open source with no paid tier).

How pricing works, briefly Pricing model detail ?

Credit-based pay-as-you-go with 0% markup and no platform fee on tokens. Monetizes gateway features à la carte: provider allowlists, ZDR, custom reporting writes/queries, Trace Drains. Enterprise can pay by invoice with no processing fees. Pricing page last updated 2026-08-23. Not verified

A one-paragraph description that covers the caveats a pricing category cannot: introductory rates, per-feature meters, tier gating, and pricing that resets on a specific date.

Minimum commitment Minimum commitment ?

None. Credits purchasable at any time with no obligation to renew; custom volume discounts on Enterprise. Not verified

Whether the vendor requires a minimum contract term, a minimum spend, or a provisioned-capacity purchase to get its published rate.

Charges that fire after you go over an allowance Overage terms ?

Trace Drains meter trace events delivered and trace data transferred; Pro plans include no allowance for either. Team-wide provider allowlist: $0.10 per 1,000 successful requests. Team-wide zero data retention: $0.10 per 1,000 requests. Custom Reporting: $0.075 per 1,000 tag/user/quota-entity writes and $5 per 1,000 reporting-endpoint queries. All billed outside credits. Not verified

The line items that scale with usage after an included allowance is exhausted — log storage, extra requests, per-feature meters, data export — which is where cost estimates usually go wrong.

Prompt cache offered Cache mechanism ?

No gateway-owned cache Not verified

Whether the gateway offers its own response cache, what kind of match it does (exact request, prefix, semantic), or simply passes provider caching through unchanged.

Discount on cached input Cache-read discount ?

Not published Not verified

How much cheaper cached tokens are than fresh input, when the vendor publishes a single figure. Bundled-inference clouds usually price this per model instead of as one number.

Premium on cache writes Cache-write premium ?

Not published Not verified

How much more the first write of a cached prefix costs versus a plain input token. A high write premium and a low hit rate can leave you paying more than you save, so this matters as much as the read discount.

Who captures the cache saving Cache economics ?

Pricing page does not state whether the gateway caches or passes through provider caching, and no cached-token pricing is published. Because Vercel charges provider list price with 0% markup, any provider cache discount would reach the customer unchanged. Not verified

Whether the customer keeps the full saving from caching or the vendor captures part of it — and any conditions attached (write premium, storage fees, best-effort hits).

What you can split spend by Cost attribution ?

By tags, user IDs and quota entity IDs via Custom Reporting (queried through the reporting endpoint at $5/1k queries). Per team/key/customer not explicitly stated. Not verified

The dimensions the vendor documents for splitting spend — per key, per user, per team, per tag, per customer. Matters if you need to chargeback internally or bill an end customer.

How you get cost data out Cost export ?

Reporting API plus Trace Drains (Pro/Enterprise, metered). CSV/S3/warehouse not stated. Not verified

The mechanisms the vendor publishes for exporting cost and usage data: CSV, an API, webhooks, S3, a data warehouse, or nothing at all. Any per-unit price is included.

Who pays the model bill BYOK mode ?

Your keys or their credits Not verified

Whether you bring your own provider accounts (BYOK), buy inference from this vendor, or can do either. This is the single biggest commercial difference between these products: it decides who holds the contract with the model provider and who carries the spend.

Catalog

Models available Models available ?

200–350 Verified 2 days ago

How many models you can call, shown as a range because several vendors publish different totals on different pages. Vendor-reported either way, so counts are not directly comparable — some count every provider variant of the same model separately.

Model providers reachable Upstream providers ?

Not published Not verified

How many distinct model providers or labs you can reach, shown as a range where the vendor’s own pages disagree. More providers usually means better redundancy when one has an outage.

Works with standard OpenAI code OpenAI-compatible API ?

Yes Verified 2 days ago

If yes, you can usually switch to it by changing one base URL, and switch away just as easily. This is the main defence against lock-in.

OpenAI chat endpoint POST /v1/chat/completions ?

Yes Not verified

The endpoint almost every application ports first. "Not documented" means the vendor never states it, which is different from a documented no.

Anthropic messages endpoint POST /v1/messages ?

Yes Not verified

Whether Anthropic-shaped calls work without rewriting them. Several products support this only as SDK compatibility or provider passthrough rather than a native endpoint — the detail page says which.

OpenAI Responses endpoint POST /v1/responses ?

Yes Not verified

The newer stateful OpenAI surface. Support is much thinner across this market than chat completions.

Embeddings endpoint POST /v1/embeddings ?

Yes Not verified

Whether you can generate vectors through the same gateway, or need a second integration for retrieval workloads.

Image generation endpoint POST /v1/images/generations ?

Yes Not verified

Whether image models are reachable through the same surface as text.

Audio endpoints POST /v1/audio/* ?

Yes Not verified

Speech-to-text and text-to-speech. Frequently the first gap in an otherwise complete gateway.

Batch jobs endpoint POST /v1/batches ?

Not documented Not verified

Asynchronous bulk processing, usually at a discount. Commonly undocumented, and commonly the reason a migration stalls late.

Needs the vendor’s own code library Requires a vendor-specific SDK ?

No Verified 2 days ago

A proprietary client library spreads through your codebase and has to be torn out again if you leave. “No” is the better answer here, and it means the standard OpenAI client works.

You can export your request history Logs / usage data export ?

Yes Verified 2 days ago

Whether you can get your own request logs, traces, or usage records back out — through an API, a bulk export, or a download. Decides whether you leave with your history or abandon it.

Settings can live in version control Declarative config-as-code ?

Not published Not verified

Whether routing, fallback, and budget rules can be declared in a file you keep in Git, rather than existing only as settings clicked into a hosted dashboard.

Embeddings Embeddings ?

Yes Verified 2 days ago

Text-to-vector models, needed for search and retrieval features.

Image generation Image generation ?

Yes Verified 2 days ago

Whether image models are reachable through the same interface.

Speech and audio Speech and audio ?

Yes Verified 2 days ago

Text-to-speech or transcription models through the same interface.

Video generation Video generation ?

Yes Verified 2 days ago

Whether video models are reachable through the same interface.

Batch processing Batch processing ?

Not published Not verified

Submitting large jobs for cheaper, slower processing. Often 50% off for work that is not time-sensitive.

Routing & reliability

Uptime it promises in writing Contractual SLA uptime ?

99.99% Not verified

The uptime percentage in a published, contractual service level agreement. A public status page is not an SLA — it reports what happened, it does not promise anything or pay you back when it breaks.

Automatic failover Automatic failover ?

Yes Verified 2 days ago

When a model provider goes down or rate-limits you, traffic moves to a backup automatically instead of returning errors to your users.

Load balancing Load balancing ?

Yes Verified 2 days ago

Spreads requests across several providers or keys to raise your effective rate limit.

Rule-based routing Conditional routing ?

Yes Verified 2 days ago

Send different requests to different models based on rules — for example a cheap model for free users and a strong model for paying ones.

Response caching Response caching ?

Yes Verified 2 days ago

Reuses the answer when the exact same request comes in again, which cuts both cost and latency.

Similar-question caching Semantic cache ?

No Verified 2 days ago

Reuses an answer when a new question means roughly the same thing as an earlier one. Saves far more than exact-match caching but can return subtly wrong answers if tuned loosely.

Where you set the timeout Request timeout surface ?

Per request Not verified

`providerOptions.gateway.providerTimeouts` in milliseconds, minimum `1000`, maximum `789000`. It measures time until the provider starts streaming and is cleared on the first token. **BYOK only.** Default value not stated ([Vercel provider timeouts](https://vercel.com/docs/ai-gateway/models-and-providers/provider-timeouts)).

Where a request timeout can be set: per request, in a config file, in the vendor dashboard, or nowhere. Nine of the twenty products documented here do not describe a request timeout at all, so the worst case of a hung upstream call is unknowable from the docs.

Where you set retries Retry policy surface ?

Not documented Not verified

No retry count or backoff strategy on the fetched pages; the documented recovery path is the fallback model list. Default: `n.a.` ([Vercel model fallbacks](https://vercel.com/docs/ai-gateway/models-and-providers/model-fallbacks)).

Where retry count and backoff are configured. Worth knowing alongside billing: a retried streaming call can be charged more than once.

Where you set fallbacks Fallback surface ?

Per request Not verified

ORDERED: a `models` array tried in order (with a top-level `models` shorthand on the Chat Completions surface) ([Vercel model fallbacks](https://vercel.com/docs/ai-gateway/models-and-providers/model-fallbacks)).

Where the fallback chain is defined. Almost every product claims fallback; the useful question is whether you can change it from code or only by hand in a dashboard.

Shape of the fallback chain Fallback shape ?

Ordered list Not verified

An ordered list tries targets in sequence; a weighted split sends a percentage of traffic to each, which is what you need to trial a new model on 5% of requests. Weighted splits are much rarer than the marketing implies.

Upstream health tracking Health checks / circuit breaking ?

Fixed, cannot change Not verified

It is automatic provider selection rather than a configurable health check or breaker: default provider choice is based on "recent uptime and latency" ([Vercel provider options](https://vercel.com/docs/ai-gateway/models-and-providers/provider-options)).

Whether the product notices a failing upstream and stops sending traffic to it, and whether you can tune the thresholds. This is what turns a provider outage into a blip rather than a sustained error rate, and only four of the twenty expose it.

Cross-region failover you control Multi-region failover surface ?

Not documented Not verified

`not_documented` ([Vercel AI Gateway docs](https://vercel.com/docs/ai-gateway)).

Whether you can define what happens when a region degrades. A vendor running many regions is not the same as a vendor letting you configure failover between them; only three document a user-controlled mechanism.

Where you set load balancing Load balancing surface ?

Per request Not verified

`per_request`, without weights. Controls are `order`, `only` and `sort` (`'cost'`, `'ttft'`, `'tps'`); no weight key is documented ([Vercel provider options](https://vercel.com/docs/ai-gateway/models-and-providers/provider-options)).

Where traffic distribution across upstreams or keys is configured.

Operations

Usage dashboards and logs Observability ?

Yes Verified 2 days ago

Built-in visibility into what was sent, what came back, what it cost, and how long it took.

Spending limits Budget controls ?

Yes Verified 2 days ago

Hard caps that stop spend before it becomes a surprise invoice. The single most valuable control for a small team.

Rate limits Rate limits ?

Yes Verified 2 days ago

Caps on request volume per key or per user, useful for protecting against abuse and runaway loops.

Separate keys per team or app Virtual keys ?

Yes Verified 2 days ago

Issue scoped keys with their own budgets and permissions so you can attribute cost and revoke access without rotating everything.

Prompt versioning Prompt management ?

Not published Not verified

Store and version prompts outside your code so they can be changed without a deploy.

Quality testing Evals ?

Not published Not verified

Built-in tooling to score model output against test cases, so you can tell whether a model swap made things better or worse.

MCP support MCP support ?

Not published Not verified

Native support for the Model Context Protocol, the emerging standard for connecting models to external tools.

What gets logged Logged content ?

Your choice Not verified

The Logs view shows a transcript of request inputs and outputs, i.e. prompt/completion text is visible, yet the same docs say "AI Gateway uses zero data retention by default" and "permanently deletes your prompts and responses after requests complete" ([Logs](https://vercel.com/docs/ai-gateway/observability-and-spend/logs), [Security and compliance](https://vercel.com/docs/ai-gateway/security-and-compliance)) — see Contradictions

Whether full prompts and responses are stored, only metadata, or nothing. Full-body logging is the most useful debugging feature here and the one most likely to need a conversation with your compliance team.

You can turn logging off Body-logging opt-out ?

Yes Not verified

Team-wide ZDR from the AI Gateway Settings tab, or per request `providerOptions.gateway.zeroDataRetention: true`; team-wide ZDR costs $0.10 per 1,000 requests while per-request ZDR is free on Pro/Enterprise ([ZDR](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr))

Whether prompt and response bodies can be suppressed while still keeping usage metrics. Nineteen of the twenty document a way to do this; the mechanisms range from a per-request header to an organisation-wide setting.

Traces you can take elsewhere Distributed tracing ?

Not documented Not verified

`n.a.` — No OpenTelemetry or agent tracing documented for the gateway ([Observability](https://vercel.com/docs/ai-gateway/observability-and-spend/observability))

Whether the product emits OpenTelemetry, a proprietary format, or nothing. OpenTelemetry means the traces land in the tooling you already run instead of only in the vendor’s dashboard.

Where telemetry can go Export destinations ?

CSV export Not verified

CSV and JSON export from the logs view; no streaming destinations documented ([Logs](https://vercel.com/docs/ai-gateway/observability-and-spend/logs))

Documented sinks for logs and metrics. This is a good proxy for how replaceable the vendor’s own dashboard is: around twenty destinations means you never have to depend on it, while a CSV download means you do.

Can record user feedback Feedback capture API ?

No Not verified

`n.a.` ([Observability](https://vercel.com/docs/ai-gateway/observability-and-spend/observability))

Whether there is an API to attach a rating or score to a logged request, which is what lets production traffic feed quality work later.

Scores live traffic Online eval hooks ?

No Not verified

`n.a.` ([Observability](https://vercel.com/docs/ai-gateway/observability-and-spend/observability))

Whether automated scorers can run against real production requests, rather than only against a test set you assemble yourself.

Performance

Delay it adds Proxy overhead ?

Not published Not verified

Extra time the product itself adds to each request, on top of however long the model takes. Usually irrelevant next to multi-second model latency, but it matters for high-volume or streaming-sensitive workloads.

Requests per second ceiling Throughput ?

Not published Not verified

Published sustained request rate before the product becomes the bottleneck. Only relevant at genuinely high volume.

What the request path runs on Architecture class ?

Undisclosed vendor service Not verified

No runtime is disclosed anywhere on the fetched Vercel AI Gateway docs, so it is classified `vendor_saas` on that basis ([Vercel AI Gateway docs](https://vercel.com/docs/ai-gateway)).

The comparable way to talk about latency here. An edge worker, a compiled Go or Rust binary, and a Python proxy have different overhead floors no matter which figures each vendor publishes. Products that never disclose their runtime are recorded as undisclosed rather than assumed.

You can run the request path yourself Self-hostable data plane ?

No Not verified

No self-host artifact is offered on the fetched docs ([Vercel AI Gateway docs](https://vercel.com/docs/ai-gateway)).

Whether the component that actually carries your prompts can run on your own infrastructure. Distinct from a vendor offering a self-hosted control plane while still proxying traffic through their network.

Streaming responses Streaming support ?

Yes Not verified

Supported. Documented caveats: "Some providers don't support stream cancellation" and "You may still be charged for timed-out requests"; the provider timeout only covers time-to-first-token and is cleared once streaming starts ([Vercel provider timeouts](https://vercel.com/docs/ai-gateway/models-and-providers/provider-timeouts)).

Whether token-by-token streaming is documented. The caveats matter more than the yes: some products cannot cancel a stream without still being billed, and several timeout and fallback mechanisms stop applying once the first token has been sent.

Security & compliance

Does your prompt reach their servers Prompt transits vendor ?

Yes Not verified

Hosted only, with primary processing facilities in the United States.

Whether the text you send passes through this company’s own infrastructure. If it does, every other promise on this page is a policy commitment rather than a physical impossibility. Self-hosted products can answer no outright.

What they keep if you change nothing Logging default ?

Yes — prompts and replies Not verified

Vercel's own documentation contradicts itself here. The logs page shows captured inputs and outputs in a transcript view; the security overview states the gateway uses zero data retention by default; the ZDR page scopes ZDR to paid tiers. Get the behaviour for your specific tier in writing before you rely on it.

Defaults matter more than options. A product that stores full prompts and replies unless you find the right header will have stored them by the time you read the docs.

How long they keep it Default content retention (days) ?

30 days Not verified

Routing attempt details are kept for 30 days. Prompts and outputs are kept for zero days where ZDR actually applies — which is the point the documentation disagrees on.

Default retention for request content, in days. Zero means nothing is kept. Read the note: several products keep nothing as a rule but make timed exceptions for abuse review or specific models.

Could they train on your prompts Training on customer data ?

No Not verified

Vercel does not use your prompts or responses for training. Separately, it does not by default avoid providers that do — you must set disallowPromptTraining to filter those out.

Whether the vendor may use your prompts and outputs to train models. “Not published” means we could not find any position, which is not the same as a no — ask for it in writing.

Where it runs, and what you can pin Region and residency control ?

US primary, and the data-processing agreement permits transfer anywhere in the world. No customer-VPC option and no documented gateway region pinning. Not verified

Which regions are offered and whether you can force processing to stay in one. A global endpoint that silently picks a region is a different compliance story from an endpoint you pin yourself.

Where safety filters run Guardrail execution location ?

No guardrails offered Not verified

No guardrails or PII redaction is documented. The security surface is ZDR plus routing filters on provider training policy.

A filter that strips personal data only helps if it runs before the data leaves your boundary. If guardrails execute in the vendor’s cloud, the vendor has already received whatever you wanted redacted.

Who else touches the data Subprocessor list ?

https://security.vercel.com/ Not verified

The published list of third parties the vendor passes your data to. No list means you cannot know the full chain, which most data-protection agreements require you to.

SOC 2 audited SOC 2 audited ?

Yes Verified 2 days ago

An independent audit of security controls. Enterprise buyers and their procurement teams routinely require it.

Will sign a HIPAA agreement HIPAA BAA ?

Yes Verified 2 days ago

Required before you may send protected health information through the service. Without a signed BAA, healthcare data is off limits.

GDPR commitments GDPR commitments ?

Yes Verified 2 days ago

Published data processing terms for handling personal data of people in the EU and UK.

Can keep data in the EU EU data residency ?

Not published Not verified

Requests can be processed inside the EU rather than routed to US infrastructure. Often the deciding constraint for European customers.

Does not retain your data Zero data retention ?

Yes Verified 2 days ago

Prompts and responses are not stored after the request completes. Sometimes a paid add-on rather than the default.

Strips personal data PII redaction ?

Not published Not verified

Detects and removes identifiers such as names, emails, and card numbers before the request reaches the model provider.

Content guardrails Content guardrails ?

No Verified 2 days ago

Policy checks on inputs and outputs — blocking unsafe content, enforcing formats, or catching prompt-injection attempts.

Runs fully disconnected Air-gapped deployment ?

No Verified 2 days ago

Can be deployed in a network with no internet access, which some regulated and defence environments require.

Blocks personal data in prompts PII / DLP enforcement ?

Not documented Not verified

The security and compliance section documents allowlists and ZDR, and states nothing about PII detection ([Security and compliance](https://vercel.com/docs/ai-gateway/security-and-compliance))

Whether personal data detection sits on the request path and can stop the call, merely inspects and forwards it, or is not documented. A control that only reports is a logging feature, not a policy control.

Blocks prompt injection Injection / jailbreak enforcement ?

Not documented Not verified

`not_documented` ([Security and compliance](https://vercel.com/docs/ai-gateway/security-and-compliance))

Whether injection and jailbreak detection can stop a request. Most products offering this call a partner classifier rather than shipping their own.

Blocks harmful content Toxicity / moderation enforcement ?

Not documented Not verified

`not_documented` ([Security and compliance](https://vercel.com/docs/ai-gateway/security-and-compliance))

Whether hate, violence, sexual and self-harm categories are checked inline and can stop a request, in either direction.

Your own policy rules Custom policy hooks ?

Not documented Not verified

No regex/word-list/JSON-schema policy engine ([Security and compliance](https://vercel.com/docs/ai-gateway/security-and-compliance))

Whether you can add your own rule — a regex, a webhook, or your own classifier — rather than choosing from the vendor library.

Where guardrails run Guardrail execution location ?

On the vendor's servers Not verified

Whether guardrail evaluation happens inside your infrastructure or on the vendor’s servers. This decides whether the prompt you are trying to protect leaves your network in order to be checked.

If the guardrail itself fails Guardrail failure mode ?

Not documented Not verified

There is no guardrail service; the analogous documented failure is ZDR routing, which fails closed with a `no_providers_available` 400 error when no ZDR provider can serve the model ([ZDR](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr))

What happens when the guardrail service times out or errors: does the request proceed unchecked, or is it blocked? This is the worst-documented field in the entire catalogue — only two vendors state it plainly, which means most teams are running a control whose failure behaviour they cannot know.

Third-party guardrail vendors Guardrail integrations ?

Not published Not verified

Named external guardrail services the product can call. A long list means the product is a router for policy engines rather than a policy engine itself — which also means another vendor bill and another hop.

Fit & integration

Work to try it Evaluation work shape ?

Install a package Not verified

The shape of the work on the vendor’s own quickstart, from swapping one base URL through to deploying infrastructure. An ordinal class rather than a duration, because elapsed time depends on accounts and quota we cannot see.

Work to run it Production work shape ?

Install a package Not verified

The same scale applied to the vendor’s recommended production path. For several products this is much heavier than the quickstart, which is exactly why both are recorded.

Steps on the quickstart Numbered quickstart steps ?

5 Not verified

A literal count of numbered steps on the vendor’s quickstart, recorded as evidence beside the work shape. Zero means the page publishes no numbered procedure at all. Large counts usually mean interleaved language tracks rather than more work.

Can you self-host it today Self-host install documentation ?

No self-hosting Not verified

Whether an install command is actually published. Several products advertise self-hosting while publishing no command to start from, which a plain yes/no would hide.

Works with the OpenAI SDK OpenAI SDK drop-in ?

Yes Not verified

Yes. Existing OpenAI client libraries can be used by setting the base URL to `https://ai-gateway.vercel.sh/v1` and authenticating with an AI Gateway API key or Vercel OIDC token. ([OpenAI Chat Completions integration](https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions))

Whether an existing OpenAI-compatible client can be pointed at it by changing the base URL and key.

Vercel AI SDK support AI SDK provider package ?

Official provider package Not verified

Vercel AI Gateway works with the Vercel AI SDK. The documented npm package is `ai` (`npm install ai@latest`), and the AI Gateway provider is available through `@ai-sdk/gateway`; OpenAI-compatible access can also use `@ai-sdk/openai-compatible`. ([AI SDK integration](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk))

Whether a first-party AI SDK provider package exists, or only a community package, a documented workaround, or the generic OpenAI provider pointed at a custom base URL.

Python framework integrations Documented Python frameworks ?

LangChain, LlamaIndex Not verified

Official documentation covers LangChain through the Chat Completions endpoint and LlamaIndex through `llama-index-llms-vercel-ai-gateway`; the LlamaIndex class is `VercelAIGateway` from `llama_index.llms.vercel_ai_gateway`. ([AI Gateway Python SDKs](https://vercel.com/docs/ai-gateway/sdks-and-apis/python))

LangChain, LangGraph, LlamaIndex and similar orchestration frameworks with a documented integration.

Callable from Cloudflare Workers Cloudflare Workers support ?

Not documented Not verified

n.a. (not documented)

Whether the docs show calling this product from your own Worker. Deliberately separated from the several products whose own gateway runs on Workers, which is a fact about their infrastructure and not about your edge compatibility.

Kubernetes install Helm chart availability ?

Not documented Not verified

n.a. (not documented)

Whether a named, published Helm chart exists, versus Helm being referenced with no chart named, versus generic cluster documentation that has nothing to do with this product.

Terraform support Terraform provider or modules ?

Not documented Not verified

n.a. (not documented)

Whether you can declare this in code: an official provider, official modules, resources inside a hyperscaler’s provider, a community provider, or only Terraform code shipped in a repo.

Reuses your cloud identity Cloud IAM reuse ?

Its own OIDC token Not verified

No AWS/Azure/GCP IAM reuse is documented; instead Vercel documents OIDC-based auth with `VERCEL_OIDC_TOKEN` so deployments can call the gateway without a separate API key. ([Vercel AI Gateway authentication docs](https://vercel.com/docs/ai-gateway/authentication))

Whether you can authenticate with IAM roles, workload identity or managed identities instead of another long-lived API key. Distinguished from products that only accept static upstream provider credentials.

Fits behind your API gateway API gateway integration ?

Not documented Not verified

n.a. (not documented)

Whether AI traffic can go through a gateway you already run, and who documented that — the product’s vendor or the gateway’s.

MCP support MCP surface shape ?

MCP client tooling Not verified

Per Vercel's AI Gateway versus MCP comparison page, the Vercel AI SDK provides `createMCPClient` for converting MCP tools into AI SDK tools, while `mcp-handler` supports building and hosting MCP servers. The page also identifies `mcp.vercel.com` as an official remote MCP server with OAuth. ([AI Gateway vs MCP](https://vercel.com/i/ai-gateway-vs-mcp))

Which kind of MCP support this is: a gateway that governs many MCP servers, a hosted MCP server you connect to, MCP tools accepted inside the completion API, or client tooling. These are different products behind one acronym.

Needs your own provider key Upstream provider key required ?

Not needed Not verified

No. "AI Gateway also supports Bring Your Own Key (BYOK) for any provider listed in our catalog," i.e. optional ([AI Gateway Pricing](https://vercel.com/docs/ai-gateway/pricing)); the quickstart uses an AI Gateway key or OIDC ([Text Generation Quickstart](https://vercel.com/docs/ai-gateway/getting-started/text))

Whether an upstream provider account and key must exist before your first call works. A prerequisite rather than a step, and it can differ between the hosted and self-hosted forms of the same product.

Gate before models work Model access gate ?

Free tier sees fewer models Not verified

No approval gate, but a catalogue limit on the free tier: it includes "a subset of models, not the full catalog," and other models require purchasing AI Gateway Credits ([AI Gateway Pricing](https://vercel.com/docs/ai-gateway/pricing))

Whether an enablement click, a quota grant, a paid tier or an approval form stands between a valid key and a working model call.

Official client languages First-party client SDK languages ?

TypeScript, Python Not verified

Documented clients include OpenAI client libraries with TypeScript and Python examples, the TypeScript `ai` package, and official Python SDKs for OpenAI (`pip install openai`) and Anthropic (`pip install anthropic`); both Python SDKs provide async clients. The ecosystem documentation also lists LangChain, LlamaIndex, Mastra, Pydantic AI, LiteLLM, and Langfuse integrations. ([AI Gateway Python SDKs](https://vercel.com/docs/ai-gateway/sdks-and-apis/python))

Languages with a first-party client library. An empty list can still mean the product is usable from any language via an OpenAI-compatible SDK.

Additional charges

These are the fees that do not appear on a per-token price list, and they are where estimates usually go wrong.

• Team-wide zero data retention $0.10 per 1,000 requests (Pro and Enterprise)
• Team-wide provider allowlist $0.10 per 1,000 successful requests (Pro and Enterprise)
• Custom Reporting writes $0.075 per 1,000 tag / user ID / quota entity writes
• Custom Reporting queries $5 per 1,000 queries to the reporting endpoint
• Vercel Pro developer seat $20 per month