Bedrock models that stay in United States
Inference must execute inside United States. Of the 113 models the matrix shows as available here, 113 are served without the request leaving, and 0 are not.
Regions counted: US East (N. Virginia) (us-east-1), US East (Ohio) (us-east-2), US West (N. California) (us-west-1), US West (Oregon) (us-west-2).
What catches people here
Availability in a United States region does not mean the call stays there. Check the route column: a model reachable only through a cross-region profile is processed wherever that profile has capacity.
Stays in region 74
Callable on-demand with the bare model ID. The request is served by the region you addressed, and nothing crosses a border.
| Model | Call this ID | Input /1M |
|---|---|---|
| Jamba 1.5 Large | ai21.jamba-1-5-large-v1:0 | — |
| Jamba 1.5 Mini | ai21.jamba-1-5-mini-v1:0 | — |
| Amazon Nova Multimodal Embeddings | amazon.nova-2-multimodal-embeddings-v1:0 | — |
| Nova 2 Sonic | amazon.nova-2-sonic-v1:0 | — |
| Nova Canvas | amazon.nova-canvas-v1:0 | — |
| Nova Lite | amazon.nova-lite-v1:0 | $0.060 |
| Nova Micro | amazon.nova-micro-v1:0 | $0.035 |
| Nova Pro | amazon.nova-pro-v1:0 | $0.800 |
| Nova Reel | amazon.nova-reel-v1:0 | — |
| Nova Reel | amazon.nova-reel-v1:1 | — |
| Nova Sonic | amazon.nova-sonic-v1:0 | $0.060 |
| Rerank 1.0 | amazon.rerank-v1:0 | — |
| Titan Embeddings G1 - Text | amazon.titan-embed-text-v1 | $0.100 |
| Titan Multimodal Embeddings G1 | amazon.titan-embed-image-v1 | — |
| Titan Text Embeddings v2 | amazon.titan-embed-g1-text-02 | — |
| Titan Text Embeddings V2 | amazon.titan-embed-text-v2:0 | — |
| Claude 3 Haiku | anthropic.claude-3-haiku-20240307-v1:0 | $0.250 |
| Embed English | cohere.embed-english-v3 | — |
| Embed Multilingual | cohere.embed-multilingual-v3 | — |
| Embed v4 other route leaves | cohere.embed-v4:0 | — |
| Rerank 3.5 | cohere.rerank-v3-5:0 | — |
| DeepSeek V3.2 | deepseek.v3.2 | $0.620 |
| DeepSeek-V3.1 | deepseek.v3-v1:0 | $0.580 |
| Gemma 3 12B IT | google.gemma-3-12b-it | $0.090 |
| Gemma 3 27B PT | google.gemma-3-27b-it | $0.230 |
| Gemma 3 4B IT | google.gemma-3-4b-it | $0.040 |
| Ray v2 | luma.ray-v2:0 | — |
| Llama 3 70B Instruct | meta.llama3-70b-instruct-v1:0 | $2.65 |
| Llama 3 8B Instruct | meta.llama3-8b-instruct-v1:0 | $0.300 |
| Llama 3.1 70B Instruct | meta.llama3-1-70b-instruct-v1:0 | $0.720 |
| Llama 3.1 8B Instruct | meta.llama3-1-8b-instruct-v1:0 | $0.220 |
| Llama 3.3 70B Instruct | meta.llama3-3-70b-instruct-v1:0 | $0.720 |
| MiniMax M2 | minimax.minimax-m2 | $0.300 |
| MiniMax M2.1 | minimax.minimax-m2.1 | $0.300 |
| MiniMax M2.5 | minimax.minimax-m2.5 | $0.300 |
| Devstral 2 123B | mistral.devstral-2-123b | — |
| Magistral Small 2509 | mistral.magistral-small-2509 | $0.500 |
| Ministral 14B 3.0 | mistral.ministral-3-14b-instruct | $0.200 |
| Ministral 3 8B | mistral.ministral-3-8b-instruct | $0.150 |
| Ministral 3B | mistral.ministral-3-3b-instruct | $0.100 |
| Mistral 7B Instruct | mistral.mistral-7b-instruct-v0:2 | $0.150 |
| Mistral Large (24.02) | mistral.mistral-large-2402-v1:0 | $4.00 |
| Mistral Large (24.07) | mistral.mistral-large-2407-v1:0 | $2.00 |
| Mistral Large 3 | mistral.mistral-large-3-675b-instruct | $0.500 |
| Mistral Small (24.02) | mistral.mistral-small-2402-v1:0 | $1.00 |
| Mixtral 8x7B Instruct | mistral.mixtral-8x7b-instruct-v0:1 | $0.450 |
| Voxtral Mini 3B 2507 | mistral.voxtral-mini-3b-2507 | $0.040 |
| Voxtral Small 24B 2507 | mistral.voxtral-small-24b-2507 | — |
| Kimi K2 Thinking | moonshot.kimi-k2-thinking | $0.600 |
| Kimi K2.5 | moonshotai.kimi-k2.5 | $0.600 |
| Nemotron Nano 3 30B | nvidia.nemotron-nano-3-30b | $0.060 |
| NVIDIA Nemotron 3 Super 120B A12B | nvidia.nemotron-super-3-120b | $0.150 |
| NVIDIA Nemotron Nano 12B v2 VL BF16 | nvidia.nemotron-nano-12b-v2 | — |
| NVIDIA Nemotron Nano 9B v2 | nvidia.nemotron-nano-9b-v2 | $0.060 |
| GPT OSS Safeguard 120B | openai.gpt-oss-safeguard-120b | $0.150 |
| GPT OSS Safeguard 20B | openai.gpt-oss-safeguard-20b | $0.070 |
| gpt-oss-120b | openai.gpt-oss-120b-1:0 | $0.150 |
| gpt-oss-20b | openai.gpt-oss-20b-1:0 | $0.070 |
| Qwen3 235B A22B 2507 | qwen.qwen3-235b-a22b-2507-v1:0 | $0.220 |
| Qwen3 32B (dense) | qwen.qwen3-32b-v1:0 | $0.150 |
| Qwen3 Coder 480B A35B Instruct | qwen.qwen3-coder-480b-a35b-v1:0 | $0.450 |
| Qwen3 Coder Next | qwen.qwen3-coder-next | $0.500 |
| Qwen3 Next 80B A3B | qwen.qwen3-next-80b-a3b | $0.140 |
| Qwen3 VL 235B A22B | qwen.qwen3-vl-235b-a22b | $0.530 |
| Qwen3-Coder-30B-A3B-Instruct | qwen.qwen3-coder-30b-a3b-v1:0 | $0.150 |
| Stable Diffusion 3.5 Large | stability.sd3-5-large-v1:0 | — |
| Stable Image Core 1.0 | stability.stable-image-core-v1:1 | — |
| Stable Image Ultra 1.0 | stability.stable-image-ultra-v1:1 | — |
| Marengo Embed 3.0 | twelvelabs.marengo-embed-3-0-v1:0 | — |
| Pegasus v1.2 other route leaves | twelvelabs.pegasus-1-2-v1:0 | — |
| Writer Palmyra Vision 7B | writer.palmyra-vision-7b | $0.150 |
| GLM 4.7 | zai.glm-4.7 | $0.600 |
| GLM 4.7 Flash | zai.glm-4.7-flash | $0.070 |
| GLM 5 | zai.glm-5 | $1.00 |
This holds for as long as you address the bare model ID. Swapping it for a
global. or cross-region profile ID is a one-word change
that moves the inference, and the models tagged
other route leaves are
the ones where that alternative exists.
Stays in jurisdiction 39
Reachable only through a cross-region inference profile, but every region that profile declares is inside the jurisdiction. The call may cross a regional boundary and will not cross this one.
| Model | Call this ID | Input /1M |
|---|---|---|
| Nova 2 Lite other route leaves | us.amazon.nova-2-lite-v1:0 | $0.300 |
| Nova Premier | us.amazon.nova-premier-v1:0 | $2.50 |
| Claude 3 Sonnet | us.anthropic.claude-3-sonnet-20240229-v1:0 | $3.00 |
| Claude Fable 5 other route leaves | us.anthropic.claude-fable-5 | $10.00 |
| Claude Haiku 4.5 other route leaves | us.anthropic.claude-haiku-4-5-20251001-v1:0 | $1.00 |
| Claude Opus 4.1 | us.anthropic.claude-opus-4-1-20250805-v1:0 | — |
| Claude Opus 4.5 other route leaves | us.anthropic.claude-opus-4-5-20251101-v1:0 | $5.00 |
| Claude Opus 4.6 other route leaves | us.anthropic.claude-opus-4-6-v1 | $5.00 |
| Claude Opus 4.7 other route leaves | us.anthropic.claude-opus-4-7 | $5.00 |
| Claude Opus 4.8 other route leaves | us.anthropic.claude-opus-4-8 | $5.00 |
| Claude Opus 5 other route leaves | us.anthropic.claude-opus-5 | $5.00 |
| Claude Sonnet 4 other route leaves | us.anthropic.claude-sonnet-4-20250514-v1:0 | — |
| Claude Sonnet 4.5 other route leaves | us.anthropic.claude-sonnet-4-5-20250929-v1:0 | $3.00 |
| Claude Sonnet 4.6 other route leaves | us.anthropic.claude-sonnet-4-6 | $3.00 |
| Claude Sonnet 5 other route leaves | us.anthropic.claude-sonnet-5 | $3.00 |
| DeepSeek-R1 | us.deepseek.r1-v1:0 | $1.35 |
| Llama 4 Maverick 17B Instruct | us.meta.llama4-maverick-17b-instruct-v1:0 | $0.240 |
| Llama 4 Scout 17B Instruct | us.meta.llama4-scout-17b-instruct-v1:0 | $0.170 |
| Pixtral Large (25.02) | us.mistral.pixtral-large-2502-v1:0 | $2.00 |
| GPT-5.6 Luna other route leaves | us.openai.gpt-5.6-luna | $0.200 |
| GPT-5.6 Sol other route leaves | us.openai.gpt-5.6-sol | $4.00 |
| GPT-5.6 Terra other route leaves | us.openai.gpt-5.6-terra | $2.00 |
| Stable Image Conservative Upscale | us.stability.stable-conservative-upscale-v1:0 | — |
| Stable Image Control Sketch | us.stability.stable-image-control-sketch-v1:0 | — |
| Stable Image Control Structure | us.stability.stable-image-control-structure-v1:0 | — |
| Stable Image Creative Upscale | us.stability.stable-creative-upscale-v1:0 | — |
| Stable Image Erase Object | us.stability.stable-image-erase-object-v1:0 | — |
| Stable Image Fast Upscale | us.stability.stable-fast-upscale-v1:0 | — |
| Stable Image Inpaint | us.stability.stable-image-inpaint-v1:0 | — |
| Stable Image Outpaint | us.stability.stable-outpaint-v1:0 | — |
| Stable Image Remove Background | us.stability.stable-image-remove-background-v1:0 | — |
| Stable Image Search and Recolor | us.stability.stable-image-search-recolor-v1:0 | — |
| Stable Image Search and Replace | us.stability.stable-image-search-replace-v1:0 | — |
| Stable Image Style Guide | us.stability.stable-image-style-guide-v1:0 | — |
| Stable Image Style Transfer | us.stability.stable-style-transfer-v1:0 | — |
| Marengo Embed v2.7 | us.twelvelabs.marengo-embed-2-7-v1:0 | — |
| Palmyra X4 | us.writer.palmyra-x4-v1:0 | — |
| Palmyra X5 | us.writer.palmyra-x5-v1:0 | — |
| Grok 4.6 other route leaves | us.xai.grok-4.6 | $2.00 |
Not offered here 3
Not available in any region of this jurisdiction, by any route.
List the 3 models
Claude 3.5 Sonnet , Claude 3.5 Sonnet v2 , Claude 3.7 Sonnet
Questions
How many Bedrock models keep data in United States?
113 of the 113 models available in United States are served without the request leaving it. The remaining 0 are reachable only through cross-region inference profiles whose declared destinations sit elsewhere, or through a global profile with no published destination list.
Does availability in United States mean the model runs there?
No. A model reachable only through a cross-region inference profile is served by whichever region in that profile's scope has capacity. The API call succeeds either way, so availability and residency have to be checked separately — that is what the route column on this page is for.
What exactly is being checked here?
Two facts from the AWS Bedrock APIs, rebuilt daily: whether the bare model ID is callable on-demand in a region of this jurisdiction, and which regions each inference profile declares as destinations. The mapping from region to country is maintained by hand. This describes where inference executes; it is not legal advice and does not cover logs, retention or where your application tier runs.