Releases & Roadmap¶

stdapi.ai is under active development with regular feature releases. Five major releases delivered since launch (v1.0-v1.5) with continuous improvements.

✨ Recent Releases¶

See Release History below for the full changelog of v1.5, v1.4, v1.3, v1.2, v1.1, and v1.0 releases.

Latest: v1.5 – Advanced Reasoning & Model Compatibility (Amazon Nova 2, Claude 4.6+ adaptive reasoning, system prompt handling)

🚀 Planned Features¶

The following features may be implemented in future releases based on community demand and feedback. Implementation priority is determined by user requests and use case requirements.

Want a feature? Submit feedback on GitHub Issues.

💬 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
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
	Custom vocabularies	Amazon Transcribe - custom vocab

🎨 Image Generation¶

Provider	Endpoint/Feature	AWS Backend
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¶

v1.5.0 – Advanced Reasoning & Model Compatibility (with v1.5.1–v1.5.2 maintenance updates)¶

Introduces advanced reasoning capabilities with Amazon Nova 2 and Anthropic Claude 4.6+ adaptive reasoning, enhanced system prompt handling for broader model compatibility.

💬 Chat Completions¶

Provider	Endpoint/Feature	AWS Backend
OpenAI	System prompt handling for unsupported models	Amazon Bedrock - foundation models
Amazon Nova	Nova 2 chat model reasoning implementation	Amazon Bedrock - foundation models
Claude	Claude 4.6+ adaptive reasoning configuration	Amazon Bedrock - Claude models

Fixes & Maintenance (v1.5.1–v1.5.2)¶

v1.5.2

• Add "/" route to avoid 404 errors on root endpoint
• Fix empty system content block handling (improves AWS Bedrock Converse API compatibility)

v1.5.1

• Fix Amazon Nova Canvas image editing to fall back to TEXT_IMAGE task type when no mask is provided

v1.4.0 – Audio Enhancements & Model Compatibility¶

Expands audio capabilities with Mistral Voxtral support, speaker diarization, audio formats for chat completions, and introduces prompt caching TTL and model aliasing for better OpenAI compatibility.

💬 Chat Completions¶

Provider	Endpoint/Feature	AWS Backend
OpenAI	/v1/chat/completions audio format support	Amazon Bedrock - foundation models
OpenAI	/v1/chat/completions extended Bedrock finish reasons mapping	Amazon Bedrock
OpenAI	Prompt caching TTL support	Amazon Bedrock - prompt caching

🎙️ Speech & Audio¶

Provider	Endpoint/Feature	AWS Backend
OpenAI	/v1/audio/transcriptions diarized_json format	Amazon Transcribe
Mistral	Voxtral audio model	Amazon Bedrock - foundation models

Platform Features¶

Fixes¶

• Fix chat completion file input handling and refactor base64 decoding and MIME handling for file processing.
• Re-raise startup exceptions and disable botocore logging to improve error visibility

v1.3.0 – Image Editing & Variation Support (with v1.3.1–v1.3.5 maintenance updates)¶

Adds support for OpenAI's image editing and variation endpoints, enabling image manipulation capabilities backed by Amazon Bedrock. Includes maintenance updates for content block handling, tool call validation, streaming fixes, and TTS optimization.

🎨 Image Generation¶

Provider	Endpoint/Feature	AWS Backend
OpenAI	/v1/images/edits	Amazon Bedrock - image models
OpenAI	/v1/images/variations	Amazon Bedrock - image models

🎙️ Speech & Audio (v1.3.2)¶

Fixes & Maintenance (v1.3.1–v1.3.5)¶

v1.3.5

• Refactor content block handling to skip empty entries in assistant responses

v1.3.4

• Handle invalid tool call arguments with robust JSON content validation
• Add deprecation mapping for amazon.titan-image-generator-v2:0 → amazon.nova-canvas-v1:0

v1.3.3

• Remove premature stop condition for contentBlockStop in streaming chat completions

v1.3.2

• Support image[] array-style notation for OpenAI image edits
• Handle empty audio segments in transcription duration calculation

v1.3.1

• Improve JSON parsing for tool arguments and results
• Correct example → examples in OpenAPI model path parameter

v1.2.0 – Service Tiers, System Tools & Performance Enhancements¶

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

Platform Features¶

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

Platform Features¶

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