AWS bedrock documentation change
Summary
Updated model compatibility documentation with new API family explanations, added streaming support indicators, introduced StartAsyncInvoke and InvokeModelWithBidirectionalStream sections with model support details
Security assessment
The changes focus on API compatibility documentation and model support matrices. While StartAsyncInvoke mentions S3 output storage and InvokeModelWithBidirectionalStream requires AWS credentials, these are standard operational details rather than security fixes or new security features. No vulnerabilities or security enhancements are explicitly addressed.
Diff
diff --git a/bedrock/latest/userguide/models-api-compatibility.md b/bedrock/latest/userguide/models-api-compatibility.md index b8ddfca89..91f27fd30 100644 --- a//bedrock/latest/userguide/models-api-compatibility.md +++ b//bedrock/latest/userguide/models-api-compatibility.md @@ -5 +5 @@ -AI21AmazonAnthropicCohereDeepSeekGoogleMetaMiniMaxMistralMoonshotNVIDIAOpenAIQwenStabilityTwelveLabsWriterZ.AI +AI21AmazonAnthropicCohereDeepSeekGoogleMetaMiniMaxMistralMoonshotNVIDIAOpenAIQwenStabilityTwelveLabsWriterZ.AIModels supporting StartAsyncInvokeInvokeModelWithBidirectionalStream @@ -9 +9,9 @@ AI21AmazonAnthropicCohereDeepSeekGoogleMetaMiniMaxMistralMoonshotNVIDIAOpenAIQwe -The following tables show which Amazon Bedrock APIs are supported by each model, organized by provider. +Amazon Bedrock supports three families of runtime APIs, each designed for different integration patterns and use cases. + +**Invoke family** : `InvokeModel` handles synchronous, single-response calls. `InvokeModelWithResponseStream` returns responses as a real-time stream. `InvokeModelWithBidirectionalStream` enables full-duplex streaming for interactive applications. `AsyncInvoke` submits long-running requests asynchronously, storing output to Amazon S3. + +**Converse family** : `Converse` provides a unified, model-agnostic interface for synchronous multi-turn conversations. `ConverseStream` delivers the same experience with streaming output. + +**OpenAI-compatible family** : `ChatCompletions` implements the OpenAI Chat Completions interface, enabling existing OpenAI-based integrations to run on Bedrock with minimal changes. `Responses` API implements the OpenAI Responses interface, supporting stateful, agentic interactions with built-in tool use and conversation history management. + +We will now look at the list of APIs supported by each model. @@ -15,2 +23,2 @@ Model name | Invoke | Converse | Chat Completions | Responses -Labs Jamba 1.5 Large | ✓ | ✓ | ✗ | ✗ -Labs Jamba 1.5 Mini | ✓ | ✓ | ✗ | ✗ +**Jamba 1.5 Large*** |  |  |  |  +**Jamba 1.5 Mini*** |  |  |  |  @@ -22,16 +30,15 @@ Model name | Invoke | Converse | Chat Completions | Responses -Amazon Nova Multimodal Embeddings | ✓ | ✗ | ✗ | ✗ -Nova 2 Lite | ✓ | ✓ | ✗ | ✗ -Nova 2 Sonic | ✓ | ✗ | ✗ | ✗ -Nova Canvas | ✓ | ✗ | ✗ | ✗ -Nova Lite | ✓ | ✓ | ✗ | ✗ -Nova Micro | ✓ | ✓ | ✗ | ✗ -Nova Premier | ✓ | ✓ | ✗ | ✗ -Nova Pro | ✓ | ✓ | ✗ | ✗ -Nova Reel | ✓ | ✗ | ✗ | ✗ -Nova Sonic | ✓ | ✗ | ✗ | ✗ -Titan Embeddings G1 - Text | ✓ | ✗ | ✗ | ✗ -Titan Image Generator G1 v2 | ✓ | ✗ | ✗ | ✗ -Titan Multimodal Embeddings G1 | ✓ | ✗ | ✗ | ✗ -Titan Text Embeddings V2 | ✓ | ✗ | ✗ | ✗ -Titan Text Embeddings v2 | ✓ | ✗ | ✗ | ✗ -Titan Text Large | ✓ | ✗ | ✗ | ✗ +**Nova Multimodal Embeddings** |  |  |  |  +**Nova 2 Lite*** |  |  |  |  +**Nova 2 Sonic** |  |  |  |  +**Nova Canvas** |  |  |  |  +**Nova Lite*** |  |  |  |  +**Nova Micro*** |  |  |  |  +**Nova Premier*** |  |  |  |  +**Nova Pro*** |  |  |  |  +**Nova Reel** |  |  |  |  +**Nova Sonic*** |  |  |  |  +**Titan Embeddings G1 - Text** |  |  |  |  +**Titan Image Generator G1 v2** |  |  |  |  +**Titan Multimodal Embeddings G1** |  |  |  |  +**Titan Text Embeddings V2** |  |  |  |  +**Titan Text Large** |  |  |  |  @@ -43,9 +50,9 @@ Model name | Invoke | Converse | Chat Completions | Responses -Claude 3 Haiku | ✓ | ✓ | ✗ | ✗ -Claude 3.5 Haiku | ✓ | ✓ | ✗ | ✗ -Claude Haiku 4.5 | ✓ | ✓ | ✗ | ✗ -Claude Opus 4.1 | ✓ | ✗ | ✗ | ✗ -Claude Opus 4.5 | ✓ | ✓ | ✗ | ✗ -Claude Opus 4.6 | ✓ | ✓ | ✗ | ✗ -Claude Sonnet 4 | ✓ | ✓ | ✗ | ✗ -Claude Sonnet 4.5 | ✓ | ✓ | ✗ | ✗ -Claude Sonnet 4.6 | ✓ | ✓ | ✗ | ✗ +**Claude 3 Haiku*** |  |  |  |  +**Claude 3.5 Haiku*** |  |  |  |  +**Claude Haiku 4.5*** |  |  |  |  +**Claude Opus 4.1*** |  |  |  |  +**Claude Opus 4.5*** |  |  |  |  +**Claude Opus 4.6*** |  |  |  |  +**Claude Sonnet 4*** |  |  |  |  +**Claude Sonnet 4.5*** |  |  |  |  +**Claude Sonnet 4.6*** |  |  |  |  @@ -57,6 +64,6 @@ Model name | Invoke | Converse | Chat Completions | Responses -Command R | ✓ | ✓ | ✗ | ✗ -Command R+ | ✓ | ✓ | ✗ | ✗ -Embed English | ✓ | ✗ | ✗ | ✗ -Embed Multilingual | ✓ | ✗ | ✗ | ✗ -Embed v4 | ✓ | ✗ | ✗ | ✗ -Rerank 3.5 | ✓ | ✗ | ✗ | ✗ +**Command R*** |  |  |  |  +**Command R+*** |  |  |  |  +**Embed English** |  |  |  |  +**Embed Multilingual** |  |  |  |  +**Embed v4** |  |  |  |  +**Rerank 3.5** |  |  |  |  @@ -68,3 +75,3 @@ Model name | Invoke | Converse | Chat Completions | Responses -DeepSeek V3.2 | ✓ | ✓ | ✓ | ✗ -DeepSeek-R1 | ✓ | ✓ | ✗ | ✗ -DeepSeek-V3.1 | ✓ | ✓ | ✓ | ✗ +**DeepSeek V3.2*** |  |  |  |  +**DeepSeek-R1*** |  |  |  |  +**DeepSeek-V3.1*** |  |  |  |  @@ -76,3 +83,3 @@ Model name | Invoke | Converse | Chat Completions | Responses -Gemma 3 12B IT | ✓ | ✓ | ✓ | ✗ -Gemma 3 27B PT | ✓ | ✓ | ✓ | ✗ -Gemma 3 4B IT | ✓ | ✓ | ✓ | ✗ +**Gemma 3 12B IT*** |  |  |  |  +**Gemma 3 27B PT*** |  |  |  |  +**Gemma 3 4B IT*** |  |  |  |  @@ -84,12 +91,12 @@ Model name | Invoke | Converse | Chat Completions | Responses -Llama 3 70B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3 8B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.1 405B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.1 70B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.1 8B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.2 11B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.2 1B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.2 3B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.2 90B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 3.3 70B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 4 Maverick 17B Instruct | ✓ | ✓ | ✗ | ✗ -Llama 4 Scout 17B Instruct | ✓ | ✓ | ✗ | ✗ +**Llama 3 70B Instruct*** |  |  |  |  +**Llama 3 8B Instruct*** |  |  |  |  +**Llama 3.1 405B Instruct** |  |  |  |  +**Llama 3.1 70B Instruct*** |  |  |  |  +**Llama 3.1 8B Instruct*** |  |  |  |  +**Llama 3.2 11B Instruct*** |  |  |  |  +**Llama 3.2 1B Instruct*** |  |  |  |  +**Llama 3.2 3B Instruct*** |  |  |  |  +**Llama 3.2 90B Instruct*** |  |  |  |  +**Llama 3.3 70B Instruct*** |  |  |  |  +**Llama 4 Maverick 17B Instruct*** |  |  |  |  +**Llama 4 Scout 17B Instruct*** |  |  |  |  @@ -101,2 +108,2 @@ Model name | Invoke | Converse | Chat Completions | Responses -MiniMax M2 | ✓ | ✓ | ✓ | ✗ -MiniMax M2.1 | ✓ | ✓ | ✓ | ✗ +**MiniMax M2*** |  |  |  |  +**MiniMax M2.1*** |  |  |  |  @@ -108,13 +115,13 @@ Model name | Invoke | Converse | Chat Completions | Responses -AI Devstral 2 123B | ✓ | ✓ | ✓ | ✗ -AI Magistral Small 2509 | ✓ | ✓ | ✓ | ✗ -AI Ministral 14B 3.0 | ✓ | ✓ | ✓ | ✗ -AI Ministral 3 8B | ✓ | ✓ | ✓ | ✗ -AI Ministral 3B | ✓ | ✓ | ✓ | ✗ -AI Mistral 7B Instruct | ✓ | ✓ | ✗ | ✗ -AI Mistral Large | ✓ | ✓ | ✗ | ✗ -AI Mistral Large 3 | ✓ | ✓ | ✓ | ✗ -AI Mistral Small | ✓ | ✓ | ✗ | ✗ -AI Mixtral 8x7B Instruct | ✓ | ✓ | ✗ | ✗ -AI Pixtral Large | ✓ | ✓ | ✗ | ✗ -AI Voxtral Mini 3B 2507 | ✓ | ✓ | ✓ | ✗ -AI Voxtral Small 24B 2507 | ✓ | ✓ | ✓ | ✗ +**AI Devstral 2 123B*** |  |  |  |  +**AI Magistral Small 2509*** |  |  |  |  +**Ministral 14B 3.0*** |  |  |  |  +**Ministral 3 8B*** |  |  |  |  +**Ministral 3B*** |  |  |  |  +**Mistral 7B Instruct*** |  |  |  |  +**Mistral Large*** |  |  |  |  +**Mistral Large 3*** |  |  |  |  +**Mistral Small*** |  |  |  |  +**Mixtral 8x7B Instruct*** |  |  |  |  +**AI Pixtral Large*** |  |  |  |  +**AI Voxtral Mini 3B 2507*** |  |  |  |  +**AI Voxtral Small 24B 2507*** |  |  |  |  @@ -126,3 +133,2 @@ Model name | Invoke | Converse | Chat Completions | Responses -AI Kimi K2 Thinking | ✓ | ✓ | ✗ | ✗ -AI Kimi K2.5 | ✓ | ✓ | ✓ | ✗ -AI moonshotai.kimi-k2-thinking | ✗ | ✗ | ✓ | ✗ +**Kimi K2 Thinking*** |  |  |  |  +**Kimi K2.5*** |  |  |  |  @@ -134,3 +140,3 @@ Model name | Invoke | Converse | Chat Completions | Responses -NVIDIA Nemotron Nano 12B v2 VL BF16 | ✓ | ✓ | ✓ | ✗ -NVIDIA Nemotron Nano 9B v2 | ✓ | ✓ | ✓ | ✗ -Nemotron Nano 3 30B | ✓ | ✓ | ✓ | ✗ +**Nemotron Nano 12B v2 VL BF16*** |  |  |  |  +**Nemotron Nano 9B v2*** |  |  |  |  +**Nemotron Nano 3 30B*** |  |  |  |  @@ -142,4 +148,4 @@ Model name | Invoke | Converse | Chat Completions | Responses -GPT OSS Safeguard 120B | ✓ | ✓ | ✓ | ✓ -GPT OSS Safeguard 20B | ✓ | ✓ | ✓ | ✓ -gpt-oss-120b | ✓ | ✗ | ✓ | ✓ -gpt-oss-20b | ✓ | ✗ | ✓ | ✓ +**GPT OSS Safeguard 120B*** |  |  |  |  +**GPT OSS Safeguard 20B*** |  |  |  |  +**gpt-oss-120b*** |  |  |  |  +**gpt-oss-20b*** |  |  |  |  @@ -151,7 +157,7 @@ Model name | Invoke | Converse | Chat Completions | Responses -Qwen3 235B A22B 2507 | ✓ | ✓ | ✓ | ✗ -Qwen3 32B | ✗ | ✗ | ✓ | ✗ -Qwen3 Coder 480B A35B Instruct | ✓ | ✓ | ✓ | ✗ -Qwen3 Coder Next | ✓ | ✓ | ✓ | ✗ -Qwen3 Next 80B A3B | ✓ | ✓ | ✓ | ✗ -Qwen3 VL 235B A22B | ✓ | ✓ | ✓ | ✗ -Qwen3-Coder-30B-A3B-Instruct | ✓ | ✓ | ✓ | ✗ +**Qwen3 235B A22B 2507*** |  |  |  |  +**Qwen3 32B*** |  |  |  |  +**Qwen3 Coder 480B A35B Instruct*** |  |  |  |  +**Qwen3 Coder Next*** |  |  |  |  +**Qwen3 Next 80B A3B*** |  |  |  |  +**Qwen3 VL 235B A22B*** |  |  |  |  +**Qwen3-Coder-30B-A3B-Instruct*** |  |  |  |  @@ -163,13 +169,13 @@ Model name | Invoke | Converse | Chat Completions | Responses -AI Stable Image Conservative Upscale | ✓ | ✗ | ✗ | ✗ -AI Stable Image Control Sketch | ✓ | ✗ | ✗ | ✗ -AI Stable Image Control Structure | ✓ | ✗ | ✗ | ✗ -AI Stable Image Creative Upscale | ✓ | ✗ | ✗ | ✗