Your OpenAI & Anthropic apps on AWS. Not just chat.¶
An AI gateway you run in your own AWS account. Point Claude Code, Open WebUI, n8n, OpenClaw — or your own code — at it, and they reach 100+ models including Claude, OpenAI GPT, DeepSeek and Nova, at AWS Bedrock rates with zero markup. Adoption is quick: they point at your gateway instead of the vendor's, and the model they name is now drawn from all of them, not one vendor's list.
- client = OpenAI()
+ client = OpenAI(base_url="https://ai.yourco.com/v1")
response = client.chat.completions.create(
model="gpt-5.6-sol",
messages=messages
)
# 100+ more models, one catalogue
# same for the Anthropic SDK — point it at /anthropicBedrock throttling you? Add a region, add its quota.¶
Every AWS region has its own independent Bedrock quota. stdapi.ai routes requests across the regions you enable and retries eligible failures elsewhere — on throttling, a temporary regional outage, or a retired model. Routing happens in the gateway, so you never touch application code.
routing + failover
own quotaown quotaown quota+1quota per region — every region you enable brings its ownautoretry in another enabled region on eligible throttling or outage0code changes — routing happens in the gateway, not your app24/7multi-AZ ECS Fargate deployment via the validated Terraform module
Streaming responses can only retry before the stream opens, and asynchronous jobs stay in the region that accepted them.
One gateway, every modality you're already calling.¶
Most gateways stop at chat completions. stdapi.ai covers text, retrieval, embeddings, images, video, speech, live voice, batch inference, moderation, reranking, and file storage across the OpenAI, Anthropic, and Cohere protocols — with conversations kept server-side and continued by id instead of resent.
- /v1/chat/completions /v1/responses /anthropic/v1/messages
- /v1/embeddings /v1/vector_stores /cohere/v2/rerank
- /v1/images/* /v1/videos
- /v1/audio/speech /v1/audio/transcriptions WS /v1/realtime
- /v1/batches /anthropic/v1/messages/batches
- /v1/moderations /v1/files
3API protocols — OpenAI, Anthropic, and Cohere — from one deployment80+endpoints — text, retrieval, images, video, audio, batch, moderation, filesWSlive speech-to-speech on the OpenAI Realtime API — speech in, speech and a transcript out
Your documents answer, and the model cites them.¶
Attach a file and it is chunked, embedded and indexed in a vector bucket in your own account, then searched by meaning. Point the same endpoints at an Amazon Bedrock knowledge base you already run and it answers as a vector store too. Then hand the stores to any chat model on the Responses API: it runs the searches the turn needs and cites the files it drew on.
0extra infrastructure — no chunker, no embedding pipeline and no vector database to run beside the gateway2kinds of store behind one API — files you attach here, or a knowledge base you already run1citation per file the answer drew on, with the passages returned on request
A knowledge base is addressed under an allowlist and is never created or deleted through this API.
Every endpoint is an agent tool.¶
Agents need no HTTP glue code. stdapi.ai publishes its whole API surface over the Model Context Protocol — chat, images, audio, files, model search — so Claude Code, OpenCode, OpenClaw, LangGraph or any MCP client calls it directly. Underneath, tool calling supports the full OpenAI and Anthropic schemas and tool-choice modes.
80+endpoints exposed as named MCP tools, each with generated documentation2transports — Streamable HTTP at /mcp, SSE for older clients0HTTP client code — agents call every endpoint directlyautodiscovery — agents find every tool through the server card and API catalog
This exposes the gateway's own AI and media APIs over MCP; it is not an aggregator for third-party MCP servers.
100+ models — including OpenAI GPT and Anthropic Claude.¶
Bedrock, Bedrock Mantle, Polly, Transcribe and Comprehend all surface as models in one catalog, detected automatically at startup. On a shared endpoint they interchange by name — swapping a Polly voice for a Bedrock speech model is a one-word change, and nothing needs writing or maintaining as AWS adds and retires models. All four text APIs work with every discovered model, and retired model IDs can redirect to their supported successor instead of failing.
+ many more 0configuration — one catalog spanning Bedrock, Mantle, Polly, Transcribe and Comprehend100+models across 10+ providers in a typical multi-region catalog4text APIs on every model — passthrough or converted automatically
Deep AWS features, zero custom code.¶
Built for AWS, not around it — Bedrock-native capabilities are exposed through standard OpenAI and Anthropic parameters, with AWS AI services and S3 woven into the same API.
5AWS AI services unified — Bedrock, Polly, Transcribe, Translate, Comprehends3://direct S3 inputs in chat, images, and embeddings — generated media lands back in your bucketIAMleast-privilege reference policies documented per feature
Pay AWS rates. See which user spent them.¶
No subscriptions, no minimums, no markup on model usage. Optional cost tracking prices each call from AWS's own Price List — serving region, service tier, cached tokens, and long-context rates included. And each end user's model calls can run under their own short-lived role session, so AWS reports their spend separately in Cost Explorer and the Cost and Usage Report — from the invoice itself, not from an estimate.
0%markup on model usage — Bedrock billed by AWS directlyliverates from the AWS Price List catalog — fetched from AWS, not hand-maintainedper userspend on the AWS bill itself — grouped in Cost Explorer and the CURbatchprice on asynchronous request sets — submit a corpus, pay Bedrock's discounted batch rate
Per-request cost figures are estimated from published AWS prices, not read back from your invoice; per-user attribution is off by default and needs a role you create.
Production on AWS in two Terraform commands.¶
The validated Terraform module ships the whole stack — ECS Fargate, HTTPS, auto-scaling, and optional WAF and monitoring. It works as-is with secure defaults, and exposes advanced options for power users: VPC integration, multi-region, cost-optimized setups.
2commands from AWS Marketplace subscription to a production endpointFSBPaligned defaults out of the box — private subnets, least privilege, encryption at rest100+optional variables for power users — bring your own VPC, go multi-region, or cost-optimize
Prefer hands-off? A managed deployment service sets it up in your account — no Terraform required.
Amazon AI Amazon Bedrock Claude DeepSeek Amazon Polly Meta Llama Nvidia Qwen OpenAI GPT xAI Grok Moonshot AI Amazon Translate Mistral AI Cohere Stability AI Minimax Amazon Transcribe AI21 Labs 
Anthropic Z.ai Amazon Nova Google Gemma Luma AI Twelve Labs Amazon Comprehend Writer No third party sits between your users and your models.¶
Unlike SaaS gateways, stdapi.ai is infrastructure you run. There is no vendor endpoint in the request path — your traffic goes from your application to your own deployment to AWS.
-
Runs in your account
Inference stays on the AWS services you enable. Bedrock does not share your prompts with model providers or use them for training. -
Region allow-lists
Pin workloads to approved regions, disable global routing, or use geography-pinned inference profiles where supported. -
Customer-managed encryption
Bring your own KMS key for data at rest, with prompt and response bodies unlogged unless you enable it. -
Security Hub aligned
Terraform module built against AWS FSBP controls; GuardDuty and DNS Firewall opt-ins close the gaps.
AWS compliance certifications apply to the AWS services and regions you choose — they are not inherited by stdapi.ai or by your application. Data sovereignty & compliance guide
Verified by AWS against its technical and security requirements for AWS Marketplace.
How it compares¶
All four expose an OpenAI-compatible API in front of Amazon Bedrock — the coverage differs. stdapi.ai is AWS-only, and therefore AWS-deep: if you need multi-cloud routing or per-key spend budgets, LiteLLM is the better fit. Competitor capabilities verified against official sources on 5 August 2026.
| stdapi.ai | LiteLLM | Access Gateway | Bedrock Mantle | |
|---|---|---|---|---|
| Full multi-modal API — images, video, audio, files | full | partial | not available | not available |
| OpenAI + Anthropic + Cohere protocols | full | partial | not available | partial |
| Multi-region capacity — combine independent regional quotas | full | partial | not available | not available |
| Regional retry — throttling, region outages, retired models | full | partial | not available | not available |
| Zero-config model discovery — every region, Bedrock + Mantle | full | partial | partial | partial |
| AWS AI services & advanced Bedrock features — Polly, Transcribe, guardrails, service tiers | full | partial | partial | partial |
| Own AI & media APIs exposed as MCP tools | full | partial | not available | not available |
| Multi-provider routing beyond AWS | not available | full | not available | not available |
| Spend limits enforced at request time | not available | full | not available | not available |
| Per-request cost tracking & observability | full | full | not available | partial |
| Production AWS deployment — Terraform, auto-scaling, optional WAF | full | partial | partial | full |
MCP is not a like-for-like row: stdapi.ai exposes its own AI and media endpoints as tools, while LiteLLM gateways external MCP servers — related capabilities that solve different problems.
full partial / manual setup not available · Full comparison
Verified against the tools teams already use¶
Every integration is the same four steps: deploy, copy your endpoint URL, paste it into the tool's settings, then name a model the deployment serves — picked from the whole catalogue, not one vendor's list. There is no step five. The tools in bold are driven end to end by an automated suite against a real deployment — not just documented.
Media generation, knowledge management and team chatbots are covered too. All use cases & integration guides
Compatibility you can inspect¶
“Compatible” should mean more than one successful chat request. The test suite is public, and the same test bodies also run against the real OpenAI, Anthropic, and Cohere endpoints — so compatibility is measured against the originals, not asserted.
-
6,000+ test cases
Run against real AWS services rather than mocks. -
20 client & framework suites
Real CLIs, apps, and libraries driven end to end against a live deployment. -
100+ model-probe records
Committed observations of what each model actually accepts and rejects. -
80+ MCP API tools
Every exposed tool called end to end through the official MCP client. -
95%+ branch coverage
Measured across the full suite, with every test tier enabled.
Inspect the public test suite · what each client suite exercises
Transparent pricing¶
Start local, graduate to AWS — same API, same SDKs. And zero lock-in: leaving is the same client-side change that got you in.
Per running container — the Terraform module defaults to one per Availability Zone. No markup on model usage: pay Bedrock rates directly. Hardened container, Terraform module, commercial support (1 business day), no AGPL obligations. Billed through AWS Marketplace onto your existing AWS invoice — no new vendor onboarding.
Custom terms and duration, committed usage, and a preferential rate — procured through your existing AWS relationship, so there's no new vendor to onboard. Want to try first? Use the free trial, then accept your offer.