Managed only Proprietary hosted service

SteadyGateway Managed marketplace

SteadyGateway is a managed marketplace with an OpenAI-compatible API; it publishes no model count. Its fees are not published. It cannot be self-hosted. It publishes neither zero data retention nor a HIPAA BAA. It handles request logging.

· 145 dated entries · 145 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.

Classified editorially as managed model access: the vendor buys official upstream capacity and quotes access, regions and reservations under one agreement. Customer-owned provider-key support and the fee split are not published. This is not evidence of a grey-market relay.

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 the hosted commercial path is documented; region placement and isolation do not establish customer-operated deployment.

Hosted access through a contract-defined endpoint. A self-hosted or VPC installation package is not established in the reviewed public pages.

API surfaces your code can keep using

0 of 7 documented, 2 partial
  • OpenAI chat POST /v1/chat/completions Partly *

    GLM example uses the OpenAI client and chat.completions.create. Endpoint and key are supplied by contract. Not API-tested; not a promise of model-wide parity.

  • Anthropic messages POST /v1/messages Not documented
  • OpenAI Responses POST /v1/responses Partly *

    Qwen example uses OpenAI responses.create with a contract-defined base URL and key. Not API-tested; upstream capability lists do not prove gateway-wide parity.

  • Embeddings POST /v1/embeddings Not documented
  • Images POST /v1/images/generations Not documented
  • Audio POST /v1/audio/* Not documented
  • Batch jobs POST /v1/batches Not 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.

The site publishes OpenAI-compatible chat and Responses request shapes for named models. Other API surfaces, streaming, tool-call and error-handling parity must be confirmed in a scoped pilot.

How much it reaches

Models Not published
Upstream providers Not published

Do not equate the named coverage examples with an API inventory. Availability depends on the agreed model list and region.

Named model families are not a count of independent upstream endpoints. The vendor names Alibaba Cloud Model Studio but publishes no complete upstream-provider inventory.

Whose models: Third-party model access; the vendor describes official provider APIs as its upstream.

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 no documented export

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

    The homepage describes vendor-operated upstream failure handling and routing. Reserved pricing describes fallback to on-demand; neither establishes a configurable cross-provider/model chain.

  • Load balancing Not documented

    Isolated capacity is a vendor scope claim, not documentation of weighted or configurable load balancing.

  • Upstream health tracking Not documented
  • Cross-region failover Not documented

    Region placement is scoped per workload. Public material does not specify automated cross-region failover or a caller configuration surface.

Confirm timeout, retry, idempotency, spillover billing and failure semantics in the pilot. No measured performance or configurable reliability feature is inferred from the 99.9% contractual commitment.

How fast the hop is

Undisclosed vendor service

The vendor does not disclose what the request path runs on, so no overhead floor can be inferred at all.

Vendor-operated capacity and routing; implementation runtime and complete data-plane architecture are not published. Architecture disclosure is offered under NDA.

You can run the request path yourself Not documented
Streaming Not documented

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 path

No 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

No documented export
What gets logged Not documented

The vendor does not state what is captured.

You can turn bodies off Not documented
Traces Not documented

Request-level reporting is mentioned, but whether content, metadata or both are stored is not published.

Where telemetry can go

No documented export. Whatever this product records stays in its own interface, so it cannot become part of the monitoring you already run.

Records user feedback Not documented
Scores live traffic Not documented

Retention: Reporting availability does not establish a retention period or deletion mechanism.

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: base url swap to run: base url swap fits 2 of 10 common stacks

Getting to a first call

Not documented
Shape of the work Change one base URL

Your existing OpenAI-compatible client keeps working. You change a base URL and a key, and nothing else in your code moves.

Read off: the vendor’s own quickstart — not documented.

Before step one

  • Your own provider key Not documented

    Not stated in the docs.

    The documented example uses a SteadyGateway-issued key; whether customer-owned upstream keys are required or accepted is not publicly specified.

  • Payment method Not documented

    Public sales-led onboarding does not state a card requirement; do not assume no card or free pilot.

  • Gate before models answer Approval required

    A form, subscription or approval sits between you and the model. Plan for a wait you do not control.

    Request production access by email; a scoped pilot and written quote precede access. No immediate public-model entitlement is established.

Everything you need first: Contact the vendor, scope exact models, region and volume, agree a pilot and obtain an endpoint/key before the shown client request can work.

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.

Shape of the work Change one base URL

Your existing OpenAI-compatible client keeps working. You change a base URL and a key, and nothing else in your code moves.

What production needs: Written commercial agreement, monthly commitment, model list, capacity/region boundary, version policy, service remedies and workload-specific data/security review.

Can you run it yourself

Install command published Not documented

A customer deployment package has not been established in the reviewed documentation.

How it fits your stack

2 of 10

Each 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
  • Fits Nothing — plain Node or Python Change one base URL.

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.

    The hosted service manages upstream access and capacity rather than being a gateway deployment tool.

  • Cloud identity Not documented

    No identity integration published. Expect API keys in a secret store.

  • MCP Not documented

    No MCP support published.

Python frameworks None documented
First-party client libraries
  • JavaScript

Public model pages show the OpenAI JavaScript client with a contract-defined base URL and key.

Agent features: Named upstream models describe capabilities, but a gateway-wide tools, agent-loop or MCP contract is not published.

Contact → scoped pilot → contract. Base-URL-swap classification describes client code only, not instant self-service signup or time to first call.

The homepage describes agent frameworks, coding assistants and internal apps generically. No specific framework integration or cloud-IAM/Workers/AI SDK adapter is verified.

What it does well

  • One agreement for selected model access
  • Vendor-described per-customer capacity isolation and version pinning
  • Published distinction between contractual availability and forthcoming measurements

Where it falls short

  • No public rate card or comparable gateway fee breakdown
  • Exhaustive account model inventory not published
  • Public security assurance, retention and operational benchmarks remain incomplete

Choose it when

Teams evaluating contracted access to selected Qwen, GLM, MiniMax, DeepSeek and Kimi models with scoped capacity and version policy.

Look elsewhere when

You need immediate self-service onboarding, a published price calculator, verified end-to-end ZDR, public certification evidence or a customer-deployed gateway.

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.

32 /52 Hard to leave
Portability score breakdown for SteadyGateway
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. not published —

Read the fine print: Request shapes use an existing OpenAI client, but endpoint, model eligibility and version policy are contractual. No export format, configuration portability or customer deployment is established.

3 of the 6 inputs are not published, so the highest reachable score here is 52 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.

SteadyGateway 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…

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

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 vendor's own figure
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 vendor's own figure
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

No gateway software release history is established. Model release dates and freshness checks are upstream-model evidence, not SteadyGateway release dates.

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

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
Customer-owned upstream-key support and any associated fees are not published. vendor's own figure
What the product charges to route traffic through your own provider keys.
Free tier Free tier
Not published
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
Workload-specific written quote based on model mix, region/isolation and reserved versus on-demand capacity. Production uses a monthly commitment; separate platform, token-markup and request-fee amounts are not published. vendor's own figure
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
Production is described as a contracted monthly commitment; the amount is not published. A pilot has a fixed scope, not a published free allowance. vendor's own figure
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
Reserved capacity is described as falling back to on-demand beyond the reservation; spillover prices and invoice rules require the written quote. vendor's own figure
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
Pricing discusses upstream cached-input and batch discounts. It does not establish a uniform customer discount, a semantic cache or separate gateway cache charges. vendor's own figure
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
Request-level reporting is included in the pilot description; attribution dimensions and billing export format are not published. vendor's own figure
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
A machine-readable billing/usage export and its format are not published in the reviewed pricing evidence. vendor's own figure
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

Models available Models available
Not published
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
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 vendor's own figure
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
Partly vendor's own figure
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
Partly vendor's own figure
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
Not documented
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 vendor's own figure
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
Not published
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
Not published
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
Not published
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

Uptime it promises in writing Contractual SLA uptime
99.9% vendor's own figure
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
Not published
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

The homepage describes vendor-operated upstream failure handling and routing. Reserved pricing describes fallback to on-demand; neither establishes a configurable cross-provider/model chain.

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

Region placement is scoped per workload. Public material does not specify automated cross-region failover or a caller configuration surface.

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

Isolated capacity is a vendor scope claim, not documentation of weighted or configurable load balancing.

Where traffic distribution across upstreams or keys is configured.

Operations

Usage dashboards and logs Observability
Yes vendor's own figure
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
Not documented

Request-level reporting is mentioned, but whether content, metadata or both are stored is not published.

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
Not published
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 vendor's own figure

Vendor-operated capacity and routing; implementation runtime and complete data-plane architecture are not published. Architecture disclosure is offered under NDA.

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
Not documented
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 our judgement

Editorial reading of the documented request path: the application points to a SteadyGateway endpoint, which uses official upstream provider APIs. Full data-flow architecture is available only by request.

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
Not published

Request-level reporting is offered, but default prompt/response logging, metadata fields and storage scope are not publicly specified.

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 public gateway-wide retention period or deletion schedule is established. The statement that customers retain retention choices is not a default retention commitment.

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
Not published — silence, not a no

No public SteadyGateway-specific prompt/output training policy is established; upstream policies must also be checked.

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
Region placement and region-isolated keys/quota pools are described as workload-specific written scope commitments. The processing/storage region list and transfer mechanisms are not public. vendor's own figure
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

The security guide gives buyer tests for injection, output handling and quotas; it does not document SteadyGateway-implemented guardrails, execution locations or failure defaults.

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
Not published
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

Work to try it Evaluation work shape
Change one base URL our judgement
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
Change one base URL our judgement
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
Not published
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 vendor's own figure

Named-model OpenAI client examples are documented; production access is gated and full endpoint/model parity is untested.

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 vendor's own figure

The hosted service manages upstream access and capacity rather than being a gateway deployment tool.

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 documented

The documented example uses a SteadyGateway-issued key; whether customer-owned upstream keys are required or accepted is not publicly specified.

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
Approval required vendor's own figure

Request production access by email; a scoped pilot and written quote precede access. No immediate public-model entitlement is established.

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
JavaScript vendor's own figure

Public model pages show the OpenAI JavaScript client with a contract-defined base URL and key.

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.
Back to top ↑

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 SteadyGateway charge a markup on model prices?

SteadyGateway 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 SteadyGateway be self-hosted?

No. SteadyGateway 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 SteadyGateway SOC 2 audited, and will it sign a HIPAA BAA?

SteadyGateway 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 SteadyGateway retain your prompts?

SteadyGateway does not publish a zero-data-retention position. What it logs is not documented. Retention, logging and training on customer data are three separate questions, and a vendor can answer one of them without answering the others. Each is listed with the page it was read from in the data-handling section below.

Can you use your own provider keys with SteadyGateway?

SteadyGateway 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.

Back to top ↑

What has changed here

  1. catalog entry catalog entry Not published Added to managed marketplaces source ↗
See this in the full changelog Back to top ↑

Usually weighed against

Follow updates about SteadyGateway