Back to the registry
Agent passport

stdapi.ai - OpenAI, Anthropic & Cohere AI Gateway for Amazon Bedrock

JGoutin-dev · Software Development

No attestation published

Certification per AWS Marketplace.

Provenance reach4 of 12 layers traced

Evidence tier Source Confirmed · 4 captures on record

User ratingNot rated0 reviews on the listing
Runs onUnknownContainer
ProvenanceUnknown44% of the provenance layers this product can disclose
Evidence riskHighSign in to see the basis for this band.

What the publisher says

As described on AWS Marketplace.

Most AI tools and applications speak only the OpenAI, Anthropic, or Cohere APIs and cannot reach Amazon Bedrock or the AWS AI services. stdapi.ai is a production-ready AI gateway you run in your own AWS account that makes them reachable from the tools you already use - Open WebUI, n8n, Cline, Claude Code, LangChain, and hundreds more. The client-side change is the base URL.

WHY CHOOSE STDAPI.AI

Show the rest of the publisher’s description (21 more lines)

50+ Endpoints Across Three Protocols - Chat, Responses, embeddings, reranking, images, video, audio (speech, transcription, translation), files, and moderation, served simultaneously on the OpenAI, Anthropic, and Cohere protocols. Standard SDKs connect on the base URL alone.

100+ AI Models - Anthropic Claude, OpenAI GPT and xAI Grok (via Amazon Bedrock Mantle), Moonshot Kimi, MiniMax, DeepSeek, Amazon Nova, Meta Llama, Alibaba Qwen, Zhipu GLM, Mistral, and Cohere, in a typical multi-region catalog. Models are addressed by name on one shared endpoint, and new ones appear as AWS adds them.

Runs in Your AWS Account - Inference runs on the AWS services and regions you enable, and Amazon Bedrock does not share prompts with model providers or use them for training. AWS compliance certifications apply to the AWS services and regions you choose; they are not inherited by stdapi.ai. Region allow-lists restrict where inference runs.

One Auto-Discovered Catalog - Amazon Bedrock, Bedrock Mantle, Polly (text-to-speech), Transcribe (speech-to-text with diarization), and Comprehend (moderation) surface as models on the same endpoint, discovered automatically. Amazon Translate backs the translation endpoints.

Purpose-Built for Amazon Bedrock - AWS-only by design, not a generic multi-provider proxy: reasoning modes, prompt caching, guardrails, service tiers, inference profiles, and prompt routers are all reachable through standard API parameters.

POPULAR USE CASES

Private ChatGPT Alternative and Team Bots - Deploy Open WebUI or LibreChat with multi-modal chat, RAG document analysis, and web search, or Q&A bots on Slack, Teams, and Telegram.

Workflow Automation - Connect AI to hundreds of services via n8n (Make and Zapier work through their generic HTTP modules) for support, content creation, and data processing.

AI Coding Assistants - Use Claude Code, Cline, OpenCode, OpenAI Codex CLI, Zed, or JetBrains AI Assistant in your IDE or terminal, backed by Claude, Moonshot Kimi, or Qwen Coder.

Autonomous Agents & MCP - 50+ API operations are exposed as Model Context Protocol tools over Streamable HTTP and SSE. OpenClaw, Claude Code, LangGraph, CrewAI, and other MCP clients connect with no HTTP client code, and discover capabilities from RFC 8288 Link headers and the machine-readable API catalog.

KEY BENEFITS

Regional Quota and Retry - Each AWS region carries its own Bedrock quota, and every region you enable adds its own. Eligible throttling and availability failures retry in another enabled region. Streaming retries only before the stream opens; asynchronous jobs stay in the region that accepted them.

Production Infrastructure - Two Terraform or OpenTofu commands deploy ECS Fargate with an HTTPS load balancer, auto-scaling, KMS encryption, and private-subnet defaults, following the AWS Well-Architected Framework. WAF and CloudWatch alarms are optional and off by default.

Built-in Security - API key authentication via AWS Systems Manager, CORS and SSRF protection, non-root container execution, and KMS-encrypted storage. OpenTelemetry tracing is optional.

No Vendor Lock-in - Standard OpenAI, Anthropic, and Cohere APIs, plus a free AGPL-3.0 open-source Community edition of the same gateway. Leaving is the same one-line base-URL change as arriving.

Model Deprecation Handling - When AWS retires a model, requests are redirected to its replacement, so applications keep running without a code change.

No Markup on Model Usage - Amazon Bedrock is billed to you directly by AWS at AWS rates, on the invoice you already receive. There are no per-seat fees and no minimum commitment, and private offers cover custom terms for organizations that need them.

EVIDENCE

AWS Qualified Software. 5,000+ automated test cases run against real AWS services and against the real OpenAI, Anthropic, and Cohere endpoints. 12 third-party clients are driven end to end against a live gateway. Gateway overhead is under 1 ms.

GET STARTED

Start with the 14-day free trial on AWS Marketplace, then deploy the Terraform module with terraform init and terraform apply. Guides for Open WebUI, n8n, and AI coding assistants at https://stdapi.ai.

Highlights

Highlighted by the publisher on AWS Marketplace.

Serves hundreds of OpenAI, Anthropic, and Cohere compatible applications - Open WebUI, n8n, Cline, Claude Code, LangChain, Obsidian, Slack bots, and agent frameworks such as OpenClaw, LangGraph, and CrewAI. 50+ endpoints across three protocols cover chat, embeddings, images, speech, transcription, files, and moderation, and 50+ API operations are exposed as MCP tools (Streamable HTTP and SSE). 100+ models including Claude, Kimi, DeepSeek, Nova, and Qwen are addressed by name on one endpoint.

The gateway runs in your own AWS account, so no third party sits between your users and your models. Inference stays on the AWS services and regions you enable; AWS compliance certifications apply to those services and regions and are not inherited by stdapi.ai. Terraform deploys ECS Fargate with auto-scaling, an HTTPS load balancer, VPC, and KMS encryption, following the AWS Well-Architected Framework. WAF, CloudWatch alarms, and OpenTelemetry tracing are optional.

0% markup on model usage: Amazon Bedrock is billed to you directly by AWS at AWS rates, on the invoice you already receive, so the gateway license is the only charge from us. No per-seat fees, no minimum commitment, and private offers cover custom terms for organizations that need them. A free AGPL-3.0 open-source Community edition of the same gateway is also available, so leaving is the one-line base-URL change that brought you in.

Preview

1 image
stdapi.ai - OpenAI, Anthropic & Cohere AI Gateway for Amazon Bedrock preview 1

Agent build and provenance

See the full provenance

The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.

Compliance

Government
  • FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27

Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.

Plans and pricing as listed

1 listed
Hours
  • UnitHrs
$0.10

Refund terms

As stated by the publisher on AWS Marketplace.

stdapi.ai offers refunds on a case-by-case basis. We encourage you to try our free tier first to evaluate the product before purchasing. To request a refund, contact support@stdapi.ai with your AWS Marketplace order ID and reason. Our team will review your request promptly. For more information, visit https://stdapi.ai/operations_getting_started/

Sources

Marketplace listingaws.amazon.comSource
App certificationaws.amazon.comSource
StandardEulaStandardEulaSource

Publisher resources

2 links
stdapi.ai - Main pagestdapi.aiSource
stdapi.ai - Githubgithub.comSource

Linked repositories

1 repo
stdapi-ai/stdapi.aigithub · AWS MarketplaceSource

Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.

Pricing
Paid
1 plan listed
Delivery
Container
Email support available at support@stdapi.ai for deployment assistance, configuration questions, and troubleshooting. Response within 1 business day. Community support via GitHub Issues at https://github.com/stdapi-ai/stdapi.ai/issues for bug reports, feature requests, and discussions. Comprehensive documentation at https://stdapi.ai includes Getting Started guides, API reference, integration examples, and troubleshooting guides.
Open the source listing ↗

Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.