Bedrock models that stay in India
Inference must execute inside India. Of the 70 models the matrix shows as available here, 48 are served without the request leaving, and 22 are not.
Regions counted: Asia Pacific (Mumbai) (ap-south-1), Asia Pacific (Hyderabad) (ap-south-2).
What catches people here
Availability in a India 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 46
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 |
|---|---|---|
| Titan Multimodal Embeddings G1 | amazon.titan-embed-image-v1 | — |
| Titan Text Embeddings V2 | amazon.titan-embed-text-v2:0 | — |
| Claude 3 Haiku other route leaves | anthropic.claude-3-haiku-20240307-v1:0 | — |
| Claude 3 Sonnet other route leaves | anthropic.claude-3-sonnet-20240229-v1:0 | — |
| Embed English | cohere.embed-english-v3 | — |
| Embed Multilingual | cohere.embed-multilingual-v3 | — |
| DeepSeek V3.2 | deepseek.v3.2 | $0.740 |
| DeepSeek-V3.1 | deepseek.v3-v1:0 | $0.682 |
| Gemma 3 12B IT | google.gemma-3-12b-it | $0.110 |
| Gemma 3 27B PT | google.gemma-3-27b-it | $0.270 |
| Gemma 3 4B IT | google.gemma-3-4b-it | $0.050 |
| Llama 3 70B Instruct | meta.llama3-70b-instruct-v1:0 | $3.18 |
| Llama 3 8B Instruct | meta.llama3-8b-instruct-v1:0 | $0.360 |
| MiniMax M2 | minimax.minimax-m2 | $0.350 |
| MiniMax M2.1 | minimax.minimax-m2.1 | $0.360 |
| MiniMax M2.5 | minimax.minimax-m2.5 | $0.360 |
| Devstral 2 123B | mistral.devstral-2-123b | — |
| Magistral Small 2509 | mistral.magistral-small-2509 | $0.590 |
| Ministral 14B 3.0 | mistral.ministral-3-14b-instruct | $0.240 |
| Ministral 3 8B | mistral.ministral-3-8b-instruct | $0.180 |
| Ministral 3B | mistral.ministral-3-3b-instruct | $0.120 |
| Mistral 7B Instruct | mistral.mistral-7b-instruct-v0:2 | $0.180 |
| Mistral Large (24.02) | mistral.mistral-large-2402-v1:0 | $4.80 |
| Mistral Large 3 | mistral.mistral-large-3-675b-instruct | $0.590 |
| Mixtral 8x7B Instruct | mistral.mixtral-8x7b-instruct-v0:1 | $0.540 |
| Voxtral Mini 3B 2507 | mistral.voxtral-mini-3b-2507 | $0.050 |
| Voxtral Small 24B 2507 | mistral.voxtral-small-24b-2507 | — |
| Kimi K2 Thinking | moonshot.kimi-k2-thinking | $0.710 |
| Kimi K2.5 | moonshotai.kimi-k2.5 | $0.720 |
| Nemotron Nano 3 30B | nvidia.nemotron-nano-3-30b | $0.070 |
| NVIDIA Nemotron 3 Super 120B A12B | nvidia.nemotron-super-3-120b | $0.180 |
| NVIDIA Nemotron Nano 12B v2 VL BF16 | nvidia.nemotron-nano-12b-v2 | — |
| NVIDIA Nemotron Nano 9B v2 | nvidia.nemotron-nano-9b-v2 | $0.070 |
| GPT OSS Safeguard 120B | openai.gpt-oss-safeguard-120b | $0.180 |
| GPT OSS Safeguard 20B | openai.gpt-oss-safeguard-20b | $0.080 |
| gpt-oss-120b | openai.gpt-oss-120b-1:0 | $0.180 |
| gpt-oss-20b | openai.gpt-oss-20b-1:0 | $0.080 |
| Qwen3 235B A22B 2507 | qwen.qwen3-235b-a22b-2507-v1:0 | $0.260 |
| Qwen3 32B (dense) | qwen.qwen3-32b-v1:0 | $0.180 |
| Qwen3 Coder 480B A35B Instruct | qwen.qwen3-coder-480b-a35b-v1:0 | $0.530 |
| Qwen3 Next 80B A3B | qwen.qwen3-next-80b-a3b | $0.168 |
| Qwen3 VL 235B A22B | qwen.qwen3-vl-235b-a22b | $0.620 |
| Qwen3-Coder-30B-A3B-Instruct | qwen.qwen3-coder-30b-a3b-v1:0 | $0.180 |
| GLM 4.7 | zai.glm-4.7 | $0.720 |
| GLM 4.7 Flash | zai.glm-4.7-flash | $0.080 |
| GLM 5 | zai.glm-5 | $1.20 |
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 2
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 |
|---|---|---|
| GPT-5.6 Luna other route leaves | in.openai.gpt-5.6-luna | $0.200 |
| GPT-5.6 Terra other route leaves | in.openai.gpt-5.6-terra | $2.00 |
Leaves the jurisdiction 7
The matrix shows this model as available here. It is only reachable through a profile that declares destinations outside the jurisdiction, so a share of your traffic is processed there.
| Model | Processed in |
|---|---|
| Nova Lite Amazon | Taiwan, Japan, South Korea, India, Singapore, Australia, Indonesia |
| Nova Micro Amazon | Taiwan, Japan, South Korea, India, Singapore, Australia, Indonesia |
| Nova Pro Amazon | Taiwan, Japan, South Korea, India, Singapore, Australia, Indonesia |
| Claude 3.5 Sonnet Anthropic | Japan, South Korea, India, Singapore, Australia |
| Claude 3.5 Sonnet v2 Anthropic | Japan, South Korea, India, Singapore, Australia |
| Claude 3.7 Sonnet Anthropic | Japan, South Korea, India, Singapore, Australia |
| Claude Sonnet 4 Anthropic | Taiwan, Japan, South Korea, India, Singapore, Australia, Indonesia |
Destination not bounded 15
The only route is a global profile. AWS does not publish a closed destination list for it, so no residency claim can be made either way — this is unverifiable, not merely non-compliant.
| Model | Processed in |
|---|---|
| Nova 2 Lite Amazon | not published |
| Claude Fable 5 Anthropic | not published |
| Claude Haiku 4.5 Anthropic | not published |
| Claude Opus 4.5 Anthropic | not published |
| Claude Opus 4.6 Anthropic | not published |
| Claude Opus 4.7 Anthropic | not published |
| Claude Opus 4.8 Anthropic | not published |
| Claude Opus 5 Anthropic | not published |
| Claude Sonnet 4.5 Anthropic | not published |
| Claude Sonnet 4.6 Anthropic | not published |
| Claude Sonnet 5 Anthropic | not published |
| Embed v4 Cohere | not published |
| GPT-5.6 Sol OpenAI | not published |
| Pegasus v1.2 TwelveLabs | not published |
| Grok 4.6 xAI | not published |
Not offered here 46
Not available in any region of this jurisdiction, by any route.
List the 46 models
Jamba 1.5 Large , Jamba 1.5 Mini , Amazon Nova Multimodal Embeddings , Nova 2 Sonic , Nova Canvas , Nova Premier , Nova Reel , Nova Reel , Nova Sonic , Rerank 1.0 , Titan Embeddings G1 - Text , Titan Text Embeddings v2 , Claude Opus 4.1 , Rerank 3.5 , DeepSeek-R1 , Ray v2 , Llama 3.1 70B Instruct , Llama 3.1 8B Instruct , Llama 3.3 70B Instruct , Llama 4 Maverick 17B Instruct , Llama 4 Scout 17B Instruct , Mistral Large (24.07) , Mistral Small (24.02) , Pixtral Large (25.02) , Qwen3 Coder Next , Stable Diffusion 3.5 Large , Stable Image Conservative Upscale , Stable Image Control Sketch , Stable Image Control Structure , Stable Image Core 1.0 , Stable Image Creative Upscale , Stable Image Erase Object , Stable Image Fast Upscale , Stable Image Inpaint , Stable Image Outpaint , Stable Image Remove Background , Stable Image Search and Recolor , Stable Image Search and Replace , Stable Image Style Guide , Stable Image Style Transfer , Stable Image Ultra 1.0 , Marengo Embed 3.0 , Marengo Embed v2.7 , Palmyra X4 , Palmyra X5 , Writer Palmyra Vision 7B
Questions
How many Bedrock models keep data in India?
48 of the 70 models available in India are served without the request leaving it. The remaining 22 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 India 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.