Your OpenAI & Anthropic apps, running on AWS Bedrock.¶

Change one line — the base URL. 100+ models — Claude, OpenAI GPT, DeepSeek, Nova — inside your own AWS account, at AWS Bedrock rates with zero markup. Works with Claude Code, OpenClaw, Open WebUI, n8n, and hundreds of other tools via the OpenAI, Anthropic, or Cohere SDK.

Start 14-day free trial Try locally with Docker — free

AWS Qualified Software $0.10/container-hour 0% markup on model usage Open-source Community Edition

app.py — the entire migration

- client = OpenAI()
+ client = OpenAI(base_url="https://ai.yourco.com/v1")

response = client.chat.completions.create(
    model="claude-fable-5", messages=messages
)
# same for the Anthropic SDK — point it at /anthropic

FOR PRODUCTION WORKLOADS

Bedrock throttling you? Multiply your quota across regions.¶

Every AWS region has its own independent Bedrock quota. stdapi.ai routes requests across the regions you enable and fails over automatically — on throttling, a regional outage, or a retired model. One throttled region never reaches your clients, and you never touch application code.

stdapi.ai
routing + failover

us-east-1 · own quota1× tokens/min

us-west-2 · own quota2× tokens/min

eu-west-1 · own quota3× tokens/min

throttle on one region → transparent retry on the next — the client just gets its answer

n× tokens/minute — each enabled region adds its full quota
0 errors when a region throttles — requests reroute before clients notice
0 code changes — routing happens in the gateway, not your app
24/7 multi-AZ ECS Fargate deployment via the validated Terraform module

Resilience & failover documentation

FOR EVERY MODALITY

One gateway, the entire API surface.¶

Most gateways stop at chat completions. stdapi.ai delivers the full OpenAI, Anthropic, and Cohere surface on AWS — chat with server-side stored conversations, embeddings, images, video, speech, transcription, moderation, reranking, and file storage.

/v1/chat/completions /v1/responses /v1/messages
/v1/embeddings /v2/rerank
/v1/images/* /v1/videos
/v1/audio/speech /v1/audio/transcriptions
/v1/moderations /v1/files

every parameter your SDK sends that AWS can honour — not just the common subset

3 API protocols — OpenAI, Anthropic, and Cohere — from one deployment
40+ endpoints — text, images, video, audio, embeddings, moderation, files
0 plugins or client changes — standard SDKs and tools connect instantly

API overview

FOR AI AGENTS

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.

MCP serverenabled

streamable HTTP/mcp

SSE · older clients/sse

server card/.well-known/mcp/server-card.json

openai_chat_completion openai_image_generation openai_audio_transcription anthropic_message cohere_rerank search_models

50 endpoints exposed as named MCP tools, each with generated documentation
2 transports — Streamable HTTP at /mcp, SSE for older clients
0 HTTP client code — agents call every endpoint directly
auto discovery — agents find every tool through the server card and API catalog

MCP & agent capabilities

FOR MODEL CHOICE

100+ models — including OpenAI GPT and Anthropic Claude.¶

The full Bedrock catalog plus Bedrock Mantle models, discovered automatically across your regions. Every text API works with every model, and retired models transparently redirect to their replacement — your apps never break.

+ many more

standard model names resolve automatically — no ARNs, no ID mapping

100+ models across 10+ providers, auto-discovered at startup
4 text APIs on every model — passthrough or converted automatically
0 breaking changes when a model retires — automatic fallback to its successor

FOR AWS-NATIVE TEAMS

Every AWS capability, zero custom code.¶

Built for AWS, not around it — every Bedrock-native feature is exposed through standard OpenAI and Anthropic parameters, with AWS AI services and S3 woven into the same API.

Full S3 integration Prompt caching Extended thinking Guardrails Service tiers Inference profiles Prompt routers Cross-region inference Nova web grounding Code interpreter SSML speech Speaker diarization

all via standard OpenAI & Anthropic parameters — no AWS SDK in your app

5 AWS AI services unified — Bedrock, Polly, Transcribe, Translate, Comprehend
s3:// direct S3 inputs in chat, images, and embeddings — generated media lands back in your bucket
IAM least-privilege reference policies documented per feature

All features

FOR BUDGET OWNERS

Pay AWS rates. See the cost of every request.¶

No subscriptions, no minimums, no markup on model usage. Built-in cost tracking prices every call from AWS's own Price List — serving region, service tier, cached tokens, and long-context rates included.

POST /v1/chat/completions200 · 1.9s

modelclaude-fable-5

region · tiereu-west-1 · priority

tokensin 12,410 (9,800 cached) · out 642

cost$0.048231 USD

0% markup on model usage — Bedrock billed by AWS directly
live rates from the AWS Price List catalog — fetched from AWS, not hand-maintained
1:1 per-request and per-user cost attribution across all endpoints

Cost management documentation

FOR DEVOPS TEAMS

Production on AWS in three Terraform commands.¶

The validated Terraform module ships the whole stack — ECS Fargate, HTTPS, WAF, auto-scaling, monitoring. It works as-is with secure defaults, and exposes advanced options for power users: VPC integration, multi-region, cost-optimized setups.

$ terraform init

$ terraform plan

$ terraform apply

Apply complete! endpoint_url = https://ai.yourco.com

ECS Fargate · ALB TLS 1.3 · WAF · auto-scaling · CloudWatch alarms

5min from AWS Marketplace subscription to a production endpoint
0 required configuration — secure, IP-restricted, FSBP-aligned defaults
100+ optional variables for power users — bring your own VPC, go multi-region, or cost-optimize

Deploy on AWS guide

Prefer hands-off? A managed deployment service sets it up in your account — no Terraform required.

FOR REGULATED WORKLOADS

Your data never leaves your AWS account.¶

Unlike SaaS gateways, stdapi.ai is infrastructure you run: no third party ever sits between your users and your models.

Data sovereignty by design
All inference inside your AWS account. Never shared with model providers, never used for training.
Region allow-lists
Pin workloads to approved regions for GDPR, HIPAA, and FedRAMP requirements.
Customer-managed encryption
CMK encryption mitigates CLOUD Act and FISA 702 exposure for regulated data.
Security Hub aligned
Terraform module built against AWS FSBP controls; GuardDuty and DNS Firewall opt-ins close the gaps.

Legal, healthcare (HIPAA), EU sovereignty (GDPR), FedRAMP — Data Sovereignty & Compliance guide

AWS Qualified Software
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	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 quota multiplication	full	partial	not available	not available
Automatic failover — throttling, region outages, retired models	full	partial	not available	not available
AWS AI services & advanced Bedrock features — Polly, Transcribe, guardrails, service tiers	full	partial	partial	partial
Integrated MCP server	full	not available	not available	not available
Real-time cost tracking & observability	full	full	not available	not available
Production deployment — Terraform, WAF, auto-scaling	full	not available	partial	full

full partial / manual setup not available · Full comparison

See pricing

What teams run on it¶

Every integration is the same three steps: deploy, copy your endpoint URL, paste it into the tool's settings. There is no step four.

PRIVATE CHATGPT

Enterprise chat

ChatGPT-style assistant for your organization — chat, voice, images, and RAG, with every conversation staying in your account.

Open WebUI · LobeHub · LibreChat

Open WebUI guide

CODING AGENTS

AI-assisted development

Frontier coding models in your IDE and terminal — without sending your codebase to a third-party AI cloud.

Claude Code · Codex · OpenCode · Zed

Coding assistants guide

NO-CODE AUTOMATION

AI in business workflows

Add AI steps to business processes with visual workflow builders — classification, summarization, content generation.

n8n · Dify · Langflow · Flowise

n8n guide

AUTONOMOUS AGENTS

Agents you control

Self-directed agents on infrastructure you own — with the built-in MCP server exposing every endpoint as an agent tool.

OpenClaw · Hermes · LangGraph · CrewAI

All use cases

Use cases & integration guides

Transparent pricing¶

Start local, graduate to AWS — same API, your application code never changes. And zero lock-in: leaving is the same one-line base-URL change that got you in.

Community

$0

AGPL-3.0 · Docker image · full API · local dev & open-source projects

Run with Docker

14-DAY FREE TRIAL

Commercial · AWS Marketplace

$0.10 /container-hour

No markup on model usage — pay Bedrock rates directly. Hardened container, Terraform module, commercial support (1 business day), no AGPL obligations, AWS billing.

Start 14-day free trial

Private offer · save 10%

$0.09 /container-hour

Same pay-per-use model, no minimums. Want to try first? Use the free trial, then accept your offer. Send your AWS account ID — we'll set it up directly.

Request a private offer