Adding DeepSeek to Bedrock model list

[lee]

Unable to add deepseek.r1-v1:0 as a model in AWS Bedrock Chat Model node

Error: The provided model identifier is invalid.

workflow not relevant at this stage

I have tried the full arn but same error
arn:aws:bedrock:us-west-2:590183879869:inference-profile/us.deepseek.r1-v1:0

The api request should look like this, could make a custom api node for this or does the model need adding to the list.

{
  "modelId": "deepseek.r1-v1:0",
  "contentType": "application/json",
  "accept": "application/json",
  "body": {
    "inferenceConfig": {
      "max_tokens": 512
    },
    "messages": [
      {
        "role": "user",
        "content": "this is where you place your input text"
      }
    ]
  }
}

Share the output returned by the last node

The provided model identifier is invalid.

Information on your n8n setup

• n8n version: 1.83
• Database (default: SQLite): PG
• n8n EXECUTIONS_PROCESS setting (default: own, main):
• Running n8n via AWS Kubernetes:
• Operating system:

[elsmr]

Hi @lee

Are you in an AWS region where this model is supported? You can find more information here:

Supported foundation models in Amazon Bedrock - Amazon Bedrock

n8n fetches the list of models from AWS Bedrock at this endpoint: /foundation-models?&byOutputModality=TEXT&byInferenceType=ON_DEMAND.

So if it’s not in the list, it’s probably not supported in your AWS region.

Hope this helps!