Velokey Managed marketplace
Velokey is a managed marketplace: an OpenAI-compatible API in front of 94 models from 20+ providers. Its fees are not published. It cannot be self-hosted. It publishes neither an unconditional zero-retention guarantee nor a HIPAA BAA. Beyond chat it also serves image generation. It handles failover and request logging.
· 100 dated entries · 100 source references
Access at a glance
Whether this product can work for you at all, before features matter: who pays the model bill, where it can run, and which of your existing API calls keep working. Every value is the vendor’s own claim, linked to the page it came from.
Marketplace/access layer, not a model developer.
Where it can run
1 of 5 shapes documented- Vendor-hosted
- Self-host
- Your VPC
- On-premise
- Air-gapped
Dimmed shapes are not documented by the vendor, which is not the same as unsupported.
Only hosted access verified.
Hosted service documented; no customer deployment package established.
API surfaces your code can keep using
2 of 7 documented, 1 partial- OpenAI chat
POST /v1/chat/completionsYesBearer key and /v1/chat/completions.
- Anthropic messages
POST /v1/messagesNot documented - OpenAI Responses
POST /v1/responsesYesPOST /v1/responses documented for GPT5.5; model-specific parity must be tested.
- Embeddings
POST /v1/embeddingsNot documented - Images
POST /v1/images/generationsPartly *Asynchronous task ID and polling; not a synchronous OpenAI image-response substitute.
- Audio
POST /v1/audio/*Not documented - Batch jobs
POST /v1/batchesNot documented
An asterisk marks a qualified verdict: support that is indirect (SDK compatibility or provider passthrough rather than a native endpoint), or a gap that is narrower or wider than the label suggests. Read the note before porting.
Compatibility is endpoint- and model-specific.
How much it reaches
Models: Counted from the vendor’s own published list; no aggregate total is published.
Count of entries returned by the models API on 2026-09-26. Includes every entry exposed by that endpoint; not a count of unique base models.
Vendor claims 20+ upstream providers; route pool not independently enumerated.
Whose models: Third-party models.
How it behaves in production
What happens when an upstream model is slow, wrong, or down — and what you can see and stop while it happens. Reliability features are recorded as where you configure them, not whether the vendor lists them, because almost every product here lists all of them.
0 of 6 reachable from code nothing documented on the request path 1 documented destination
When something goes wrong
Each row says where the knob is, not whether the feature is on the marketing page. A control you can only reach by hand in someone else’s dashboard cannot be reviewed or version-controlled.
- Request timeout Not documented
The vendor does not document this, so any behaviour you observe today is unversioned and may change.
- Retries Not documented
- Fallback to another model Not documented
Vendor-managed failover when healthy alternative routes are available; caller controls not documented.
- Load balancing Not documented
- Upstream health tracking Not documented
- Cross-region failover Not documented
Test failure behavior and retry billing for your selected route.
How fast the hop is
Undisclosed vendor serviceThe vendor does not disclose what the request path runs on, so no overhead floor can be inferred at all.
Implementation runtime not published.
Streaming caveats: Chat stream parameter documented; media is asynchronous.
This vendor publishes no latency or throughput figure for the routing layer. That is the most common case here, and it is why the architecture class above carries the comparison instead of a number.
What it will stop
nothing documented on the request pathNo request-path policy controls are documented. That is not a fault in a product built purely for routing — but it means anything you need blocked has to be blocked before the call reaches here.
What you can see
Export is limitedToken counts, latency and model names are stored, but not the text itself.
Operational logs; generated media storage is a separate concern.
Where telemetry can go
- Console export
Usage and transaction records.
Retention: Metadata retention period not published.
Whether it fits how you work
How much work stands between you and a first call, how different that is from running it in production, and whether it slots into the stack you already have. Recorded as the shape of the work rather than a number of minutes — how long it takes you depends on which accounts and quota you already hold, which no comparison can know.
to try: cloud console setup to run: cloud console setup fits 1 of 10 common stacks
Getting to a first call
3 numbered stepsYou cannot start from an empty editor. An account, a project or a deployed resource has to exist first, and that step is done by hand.
Read off: the vendor’s own quickstart — 3 numbered steps.
Editorial grouping: create key, configure client, select model. Not a timed test.
Before step one
- Your own provider key Not needed
You can make a first call with only this product’s key. No upstream provider account needed.
The documented credit-funded path uses a Velokey key.
- Payment method Not documented
- Gate before models answer Not documented
The docs do not say, so budget for a surprise on the first model you actually want.
Everything you need first: Account, Velokey key and eligible model.
Running it in production
The same scale applied to the path the vendor recommends for production traffic. Kept separate from the quickstart because for several products here the two are barely related pieces of work.
You cannot start from an empty editor. An account, a project or a deployed resource has to exist first, and that step is done by hand.
What production needs: Validate model capabilities, charges and data handling.
Can you run it yourself
A customer deployment package has not been established in the reviewed documentation.
How it fits your stack
1 of 10Each row is a thing you might already run. “With a caveat” means it works but not the way the vendor’s marketing implies — read the reason, because that is usually where the surprise lives.
- With a caveat The OpenAI SDK OpenAI-compatible paths are documented, but not as a general drop-in.
- No The Vercel AI SDK No AI SDK route documented.
- No Cloudflare Workers No Workers guidance published.
- No Kubernetes No Kubernetes deployment published.
- No Terraform or OpenTofu Nothing published for Terraform.
- Fits An existing API gateway This is that gateway — AI traffic becomes a plugin, not a new hop.
- No Cloud IAM I already run No identity integration published.
- No LangChain or LlamaIndex No framework integration documented.
- No MCP servers to govern Not documented
- No Nothing — plain Node or Python A cloud console or resource has to exist before your first call.
Reading this the other way round — pick what you already run and see every product scored against it.
The integration surfaces behind those answers
- Vercel AI SDK Not documented
Nothing published. Assume the OpenAI-compatible route and verify it yourself.
- Cloudflare Workers Not documented
No Workers guidance either way. If you are edge-first, verify fetch-only compatibility yourself.
- Kubernetes Not documented
No Kubernetes story published.
- Terraform Not documented
No Terraform surface published. Configuration is API or dashboard work.
- Existing API gateway It is the API gateway
This product is the gateway. If you already run it for your other APIs, AI traffic becomes a plugin rather than a new hop.
Application requests traverse the hosted service.
- Cloud identity Not documented
No identity integration published. Expect API keys in a secret store.
- MCP Not documented
No MCP support published.
OpenAI client example on homepage.
Agent features: Chat schema includes tools and tool_choice; agent framework compatibility not tested.
Use the account model endpoint to confirm routable IDs.
What it does well
- Shared account and billing
- Familiar chat interface
- Asynchronous media workflows
Where it falls short
- Conflicting output-retention statements
- Separate gateway fee percentages not published
- Enterprise assurance not established
Choose it when
Developers evaluating consolidated access to language and media models.
Look elsewhere when
You require verified end-to-end ZDR, contractual uptime or documented private deployment.
Managed marketplace: One account and one key gets you hundreds of models from dozens of providers. Fastest way to start, widest catalog, least control over the data path.
How hard is it to leave?
Derived from six published facts, not from an opinion. The weights are fixed and the same for every product — see the arithmetic.
| What helps you leave | Points | Source |
|---|---|---|
| Works with standard OpenAI code Switching away is a base-URL change rather than a rewrite of every call site. | 22 /22 | vendor page |
| No vendor-specific SDK required A proprietary client library spreads through your codebase and has to be torn out again. | 10 /10 | vendor page |
| Can use your own provider accounts Your keys and billing relationship stay yours, so removing the gateway does not cut off model access. | not published | — |
| Can be self-hosted You can run it yourself instead of accepting a pricing or policy change. | 0 /20 | vendor page |
| Configuration lives in version control Routing and budget rules are a file you keep, not dashboard state you would have to rebuild. | not published | — |
| Your request history can be exported You leave with your own logs instead of abandoning them. | 12 /12 | vendor page |
Read the fine print: Retest media task handling and each model when migrating.
2 of the 6 inputs are not published, so the highest reachable score here is 64 rather than 100. That is a gap in the public documentation, not a mark against the product — no points are deducted, they simply cannot be claimed. This measures technical switching cost only. It does not price the engineering time to re-test prompts against a different routing stack.
Velokey models & pricing
Browse every imported listing from this provider, with published token rates and a link to compare other providers for the same model. This is provider-reported coverage; an absent listing does not mean unsupported.
Loading model listings…
Official model coverage source ↗ · Model source coverage and limitations
Full specification
Every field we track. Blank fields say "Not published" rather than "No" — we do not infer an absence from silence. Switch to Technical in the header for the precise field names and the low-level details.
Overview
Interpret these fields: Self-hosted vs managed LLM gateways · Who still owns your LLM gateway?
- What kind of product Category
- Managed marketplace our judgement
- 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
- Managed means the vendor operates it. Self-host means you run it on your own infrastructure. Both means you can choose.
- Licence Licence
- Proprietary hosted service
- 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
- Not published
- The organisation that maintains the product.
- Who you would be signing with Vendor status
- Not published
- 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
- Not published
- 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
- A rough proxy for community size on open-source projects. Not a quality measure.
Cost
Interpret these fields: How LLM gateway pricing works · LLM gateway spending limits: stop a runaway agent bill?
- Markup on model prices Token markup
- Not published
- 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
- Not published
- 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
- Not published
- A recurring per-user platform charge that applies regardless of how much you use the models.
- Can use your own provider accounts BYOK supported
- Not published
- 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
- Provider-key passthrough and any associated fees are not published.
- What the product charges to route traffic through your own provider keys.
- Free tier Free tier
- $0.50 signup credit advertised; confirm current eligibility and promotional terms.
- What you can do without paying, useful for evaluation.
- Enterprise plan from Enterprise plan from
- Not published
- Annual entry price for the enterprise tier, where one is published or credibly reported.
- Cost to run it yourself Self-host cost
- Not published
- What self-hosting actually costs once you account for infrastructure and any paid tier.
- How the vendor makes money Pricing model
- Not published
- 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
- Prepaid usage credits; model-specific units. Separate markup not published.
- 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
- No plan minimums advertised; minimum credit purchase not established.
- 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
- Check retry/failure charges before production.
- 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
- Not published
- 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
- 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
- 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
- Not published
- 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
- Model, token and billing metadata.
- 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
- Usage and transaction export.
- 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
- Not published
- 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
Interpret these fields: LLM gateway model counts: what “500+” means
- Models available Models available
- 94
- 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
- 20+
- 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
- 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
- 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
- Not documented
- 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
- The newer stateful OpenAI surface. Support is much thinner across this market than chat completions.
- Embeddings endpoint POST /v1/embeddings
- Not documented
- Whether you can generate vectors through the same gateway, or need a second integration for retrieval workloads.
- Image generation endpoint POST /v1/images/generations
- Partly
- Whether image models are reachable through the same surface as text.
- Audio endpoints POST /v1/audio/*
- Not documented
- Speech-to-text and text-to-speech. Frequently the first gap in an otherwise complete gateway.
- Batch jobs endpoint POST /v1/batches
- Not documented
- 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
- 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
- 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
- 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
- Not published
- Text-to-vector models, needed for search and retrieval features.
- Image generation Image generation
- Yes
- Whether image models are reachable through the same interface.
- Speech and audio Speech and audio
- Not published
- Text-to-speech or transcription models through the same interface.
- Video generation Video generation
- Yes
- Whether video models are reachable through the same interface.
- Batch processing Batch processing
- Not published
- Submitting large jobs for cheaper, slower processing. Often 50% off for work that is not time-sensitive.
Routing & reliability
Interpret these fields: How LLM gateway failover actually works · Does your LLM gateway promise any uptime? · Is routing destroying your prompt cache? · Changing models without breaking production
- Uptime it promises in writing Contractual SLA uptime
- Not published
- 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
- 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
- Not published
- Spreads requests across several providers or keys to raise your effective rate limit.
- Rule-based routing Conditional routing
- Not published
- 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
- Not published
- Reuses the answer when the exact same request comes in again, which cuts both cost and latency.
- Similar-question caching Semantic cache
- Not published
- 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
- Not documented
- 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
- 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
- Not documented
Vendor-managed failover when healthy alternative routes are available; caller controls not documented.
- 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
- Shape not documented
- 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
- Not documented
- 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
- 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
- Not documented
- Where traffic distribution across upstreams or keys is configured.
Operations
Interpret these fields: LLM gateway observability: traces, logs and export · Running coding agents through an LLM gateway · Changing models without breaking production
- Usage dashboards and logs Observability
- Yes
- Built-in visibility into what was sent, what came back, what it cost, and how long it took.
- Spending limits Budget controls
- Not published
- Hard caps that stop spend before it becomes a surprise invoice. The single most valuable control for a small team.
- Rate limits Rate limits
- Not published
- 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
- Not published
- 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
- Store and version prompts outside your code so they can be changed without a deploy.
- Quality testing Evals
- Not published
- 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
- Native support for the Model Context Protocol, the emerging standard for connecting models to external tools.
- What gets logged Logged content
- Metadata only
Operational logs; generated media storage is a separate concern.
- 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
- Not documented
- 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
- 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
- Console export
Usage and transaction records.
- 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
- Not documented
- 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
- Not documented
- 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
- 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
- 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
Implementation runtime not published.
- 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
- Not documented
- 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
- Partly
Chat stream parameter documented; media is asynchronous.
- 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
Interpret these fields: LLM gateway compliance: SOC 2, HIPAA and evidence · How LLM gateway guardrails fail · Which LLM gateways store your prompts? · Do you need an MCP gateway as well?
- Does your prompt reach their servers Prompt transits vendor
- Yes
Requests pass through Velokey to upstream services.
- 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
- Metadata only, not content
Policy says metadata only; image-output storage conflicts with its blanket exclusion.
- 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)
- Not published
No uniform retention duration established.
- 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
Vendor excludes its own training; upstream policies apply separately.
- 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
- Not published
- 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
- Not published
- 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
- Not published
- 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
- Not published
- An independent audit of security controls. Enterprise buyers and their procurement teams routinely require it.
- Will sign a HIPAA agreement HIPAA BAA
- Not published
- Required before you may send protected health information through the service. Without a signed BAA, healthcare data is off limits.
- GDPR commitments GDPR commitments
- Not published
- 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
- 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
- Depends how you deploy it
- 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
- Detects and removes identifiers such as names, emails, and card numbers before the request reaches the model provider.
- Content guardrails Content guardrails
- Not published
- Policy checks on inputs and outputs — blocking unsafe content, enforcing formats, or catching prompt-injection attempts.
- Runs fully disconnected Air-gapped deployment
- Not published
- 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
- 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
- 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
- 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
- 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
- Not documented
- 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
- 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
- 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.
Compliance evidence
Graded by how strong the evidence is, not whether the word appears on the vendor’s website. An audited report and a marketing claim are different things, and only one of them will satisfy your own auditor.
- SOC 2 Not published
- ISO 27001 Not published
- GDPR DPA Not published
- HIPAA BAA Not published
- FedRAMP Not published
- ITAR Not published
No compliance certifications were found published for this product. That is not the same as failing an audit — it means there is nothing public to check, so ask for evidence directly.
Fit & integration
Interpret these fields: How much does an LLM gateway lock you in? · Do you need an MCP gateway as well? · Running coding agents through an LLM gateway · Changing models without breaking production
- Work to try it Evaluation work shape
- Set it up in a cloud console
- 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
- Set it up in a cloud console
- 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
- 3
Editorial grouping: create key, configure client, select model. Not a timed test.
- 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
- Not documented
- 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
- Partly
Chat-compatible; media return shapes differ.
- 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
- Not documented
- 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
- Not published
- LangChain, LangGraph, LlamaIndex and similar orchestration frameworks with a documented integration.
- Callable from Cloudflare Workers Cloudflare Workers support
- 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
- 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
- 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
- Not documented
- 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
- It is the API gateway
Application requests traverse the hosted service.
- 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
- Not documented
- 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
The documented credit-funded path uses a Velokey key.
- 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
- Not documented
- 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
- Python
OpenAI client example on homepage.
- 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.
Common questions
Answered from the fields above, so these move when the catalog moves. Every figure quoted here appears in the specification with its source.
Does Velokey charge a markup on model prices?
Velokey does not publish a token markup figure. A blank here means the vendor states no figure, not that the service is free — the pricing page it was checked against is linked in the fees section below. The cost estimator itemises this against your own volume.
Can Velokey be self-hosted?
No. Velokey is available only as a service the vendor operates; there is no self-hosted build. The licence is Proprietary hosted service. Prompts therefore leave your network and reach the vendor, which makes its retention and residency terms the control that matters here rather than deployment.
Is Velokey SOC 2 audited, and will it sign a HIPAA BAA?
Velokey publishes neither a SOC 2 report nor a HIPAA business associate agreement. Each of these is linked to the vendor's own page in the compliance section below. Neither absence means a refusal: both are things a vendor either publishes or does not, and smaller products often hold the certification without advertising it.
Does Velokey retain your prompts?
Velokey offers zero data retention conditionally rather than by default. Only metadata is logged — not prompt or response bodies. It states that it does not train on customer data. Retention, logging and training on customer data are three separate questions, and a vendor can answer one of them without answering the others.
Can you use your own provider keys with Velokey?
Velokey does not publish whether you can supply your own upstream provider keys. Bringing your own key decides whether inference is billed to you by the model provider or resold by the gateway, which is worth confirming before committing. The billing route is worth confirming with the vendor before committing.
How many models does Velokey support?
Velokey publishes no aggregate total; counting its catalog gives 94 models, drawn from 20+ upstream providers. Count of entries returned by the models API on 2026-09-26. Includes every entry exposed by that endpoint; not a count of unique base models. The figure on this page is dated and carries its source.
Official links
Independent coverage
Third-party analysis, walkthroughs and operator threads. We link criticism as readily as praise. Nothing here is written or published by the vendor, by a competitor listed on this site, or by an SEO content farm — how we vet these.
Nothing yet that clears our bar. Everything we found was written by the vendor, by a competitor, or by an SEO content farm, so we would rather show you nothing than pass marketing off as a review.
What has changed here
- Models available Models available 120 94 source ↗
- provider added provider added Not published Managed marketplace source ↗
Read the head-to-head
These pairs have a written verdict, not just a table.