Roadmap & Changelog
What's Next
The following features may be implemented in future releases based on community demand and feedback. Implementation priority is determined by user requests, use case requirements, and alignment with the project's goals. All features can be implemented using AWS services as backends. If you need a specific feature, submit feedback or contribute to discussions.
💬 Chat Completions
| Provider |
Endpoint/Feature |
AWS Backend |
 OpenAI |
/v1/completions |
 Amazon Bedrock - foundation models |
| OpenAI |
/v1/responses |
Amazon Bedrock - foundation models |
 Claude |
/v1/messages |
Amazon Bedrock - foundation models |
| Claude |
Extended thinking mode |
Amazon Bedrock - Claude thinking |
 Ollama |
/api/generate |
Amazon Bedrock - foundation models |
| Ollama |
/api/chat |
Amazon Bedrock - foundation models |
 Cohere |
/v1/chat |
Amazon Bedrock - foundation models |
 Qwen |
/v1/chat/completions translation_options |
 Amazon Translate |
🌐 Translation
| Provider |
Endpoint/Feature |
AWS Backend |
| DeepL |
/v2/translate |
Amazon Translate |
🧠 Embeddings
| Provider |
Endpoint/Feature |
AWS Backend |
| Ollama |
/api/embeddings |
Amazon Bedrock - embedding models |
| Cohere |
/v1/embed |
Amazon Bedrock - embedding models |
🔍 Semantic Search & Ranking
| Provider |
Endpoint/Feature |
AWS Backend |
| Cohere |
/v1/rerank |
Amazon Bedrock - rerank models |
📋 Model Discovery
| Provider |
Endpoint/Feature |
AWS Backend |
| Ollama |
/api/tags |
Amazon Bedrock - model listing |
| Ollama |
/api/show |
Amazon Bedrock - model details |
 Stability AI |
/v1/engines/list |
Amazon Bedrock - model catalog |
|
Model selection wildcards (To automatically latest model versions) |
Amazon Bedrock - model catalog |
🎙️ Speech & Audio
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/realtime/sessions |
 Amazon Nova Sonic |
| OpenAI |
/v1/realtime/transcription_sessions |
Amazon Nova Sonic |
|
Transcriptions with Nova Sonic |
Amazon Nova Sonic |
|
Translations with Nova Sonic |
Amazon Nova Sonic |
|
Long-form speech (async) |
 Amazon Polly - async tasks |
|
Streaming transcription |
 Amazon Transcribe - streaming |
|
Speaker diarization |
Amazon Transcribe - diarization |
|
Custom vocabularies |
Amazon Transcribe - custom vocab |
🎨 Image Generation
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/images/edits |
Amazon Bedrock - image models |
| OpenAI |
/v1/images/variations |
Amazon Bedrock - image models |
| Stability AI |
/v1/generation/text-to-image |
Amazon Bedrock - image models |
| Stability AI |
/v1/generation/image-to-image |
Amazon Bedrock - image models |
| Stability AI |
/v1/generation/image-to-image/masking |
Amazon Bedrock - image models |
| Stability AI |
/v2/stable-image/generate |
Amazon Bedrock - image models |
| Stability AI |
/v2/stable-image/upscale |
Amazon Bedrock - image models |
| Stability AI |
/v2/stable-image/edit |
Amazon Bedrock - image models |
🎯 Model-Specific Features
| Provider |
Endpoint/Feature |
AWS Backend |
|
Running Provisioned throughput |
Amazon Bedrock - provisioned models |
🤖 AWS Bedrock Advanced Features
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/agents |
Amazon Bedrock - Agents |
| OpenAI |
/v1/vector_stores |
Amazon Bedrock - Knowledge Bases |
| OpenAI |
/v1/evals |
Amazon Bedrock - Model Evaluation |
| OpenAI |
/v1/fine_tuning/jobs |
Amazon Bedrock - custom models |
📦 Batch & Async Processing
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/batches |
Amazon Bedrock - batch inference |
| Claude |
/v1/messages/batches |
Amazon Bedrock - batch inference |
🛡️ Content Safety & Moderation
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/moderations |
 Amazon Comprehend - toxicity |
📁 Files & Storage
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/files |
 Amazon S3 |
📊 Usage & Analytics
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/usage |
 Amazon CloudWatch |
| OpenAI |
/v1/organization/usage |
Amazon CloudWatch |
🔐 Authentication & Access Control
| Provider |
Endpoint/Feature |
AWS Backend |
|
User authentication |
 Amazon Cognito |
|
Multi-tenant API keys |
 Amazon DynamoDB |
|
API key rotation |
 AWS Secrets Manager |
|
Rate limiting |
Amazon DynamoDB |
|
AWS Bedrock API keys |
AWS Bedrock |
✨ Release History
Introduces service tiers and latency headers for all Bedrock routes, Bedrock-specific system tools (Nova grounding), GPT5.2 API compatibility, configurable guardrail overrides, and Python 3.14 optimization.
💬 Chat Completions
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/chat/completions service_tier parameter |
Amazon Bedrock - service tiers |
| OpenAI |
/v1/chat/completions Bedrock-specific system tools (Nova grounding) |
Amazon Bedrock - system tools |
| OpenAI |
/v1/chat/completions GPT5.2 API update (reasoning_effort=xhigh) |
|
🛡️ Content Safety & Moderation
| Feature |
AWS Backend |
| Configuration flag for guardrail override allow |
Amazon Bedrock Guardrails |
| Feature |
AWS Backend / Description |
| Service tiers and latency headers (all Bedrock routes) |
Amazon Bedrock - service tiers |
| Python 3.14 support |
Upgraded to Python 3.14 with performance optimization |
| Dependency update |
Direct aiobotocore usage (replaced aioboto3) |
Fixes
- Fix warnings for duplicated FastAPI routes (
/docs and /openapi.json).
v1.1.0 – Embeddings Enhancement, Prompt Caching & Advanced Routing
Expands multimodal embedding capabilities, adds prompt caching support, and introduces advanced routing with application inference profiles and prompt routers.
💬 Chat Completions
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
Prompt caching /v1/chat/completions prompt_cache_key |
Amazon Bedrock - prompt caching |
| OpenAI |
/v1/chat/completions GPT5.1 API update (reasoning_effort=none) |
|
🧠 Embeddings
| Provider |
Endpoint/Feature |
AWS Backend |
|
Intelligent S3 multimodal upload |
Amazon S3 |
|
Intelligent Sync/async Bedrock invocation |
Amazon Bedrock |
| Amazon Nova |
Multimodal embeddings models |
|
 Twelve Labs |
Marengo V3 models |
|
🎯 Advanced Routing
| Feature |
AWS Backend |
| Application inference profiles |
Amazon Bedrock - application inference profiles |
| Prompt routers |
Amazon Bedrock - prompt routers |
| Server-side ARN mapping |
Amazon Bedrock |
| Client-side ARN passing (optional) |
Amazon Bedrock |
Fixes
/v1/chat/completions: Fix default value passed to the converse API for tools without parameters.- stdapi-ai Terraform module: Fix error if alarms_enabled = true but sns_topic_arn undefined.
v1.0.0 – Foundation Release
The initial release establishes core OpenAI API compatibility with AWS Bedrock backing.
💬 Chat Completions
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/chat/completions |
Amazon Bedrock - foundation models |
|
All models supporting Converse/ConverseStream APIs |
Amazon Bedrock - Converse API |
 Deepseek |
/v1/chat/completions reasoning_content |
Amazon Bedrock - foundation models |
| Qwen |
enable_thinking + thinking_budget parameter |
Amazon Bedrock - foundation models |
| Qwen |
top_k parameter |
Amazon Bedrock - foundation models |
🧠 Embeddings
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/embeddings |
Amazon Bedrock - embedding models |
| Cohere |
Embed V3 & V4 models |
|
| Twelve Labs |
Marengo V2 models |
|
 Amazon Titan |
Embed V1 & V2 models |
|
🎙️ Speech & Audio
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/audio/speech |
Amazon Polly + Amazon Comprehend |
| OpenAI |
/v1/audio/transcriptions |
Amazon Transcribe |
| OpenAI |
/v1/audio/translations |
Amazon Transcribe + Amazon Translate |
🎨 Image Generation
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/images/generations |
Amazon Bedrock - image models |
| Amazon Nova |
Canvas V1 models |
|
| Amazon Titan |
Image Generator V1 & V2 models |
|
| Stability AI |
Image Core, Ultra et SD3.5 Large models |
|
📋 Model Discovery
| Provider |
Endpoint/Feature |
AWS Backend |
| OpenAI |
/v1/models |
Amazon Bedrock - model catalog |
| Feature |
AWS Backend |
| 🤖 Bedrock Features |
|
| Content filtering and safety |
Amazon Bedrock Guardrails |
| Cross-region inference |
Amazon Bedrock - global/regional |
| Application inference profiles |
Amazon Bedrock - inference profiles |
| Model parameters (temperature, top_p, etc.) |
Amazon Bedrock - native parameters |
| Multi-region failover |
Amazon Bedrock - multi-region |
| Bedrock guardrails |
Amazon Bedrock Guardrails |
| ☁️ AWS Services |
|
| File storage |
Amazon S3 - presigned URLs, Transfer Acceleration |
| 🔐 Authentication |
|
| Static token authentication |
 AWS SSM Parameter Store / Secrets Manager |
| Development mode (no auth) |
|
| 📊 Observability |
|
| Distributed tracing |
 AWS X-Ray + OpenTelemetry |
| Structured logging |
Amazon CloudWatch (When running on ECS/EKS) |
| ❤Health check endpoint |
|
| 🔒 HTTP/Security |
|
| CORS support |
|
| Trusted host validation |
|
| Proxy headers (X-Forwarded-*) |
|
| GZip compression |
|
| 📚 Documentation |
|
| Interactive API docs & OpenAPI schema |
|
| 🔌 Compatibility |
|
| Provider-specific parameters |
|