# AWS Bedrock Agent API – Chat Completion

> AWS Bedrock Agent API – Chat Completion is a paid API for AI agents from aws-bedrock-agent-api.vercel.app, paid per call via x402, $0.25/call, status unknown (last checked 2026-10-11).

Proxies chat completion requests to Amazon Bedrock models (e.g. Amazon Nova) via a pay-per-call x402/MPP payment gateway

## Facts

- Endpoint: POST https://aws-bedrock-agent-api.vercel.app/api/chat?utm_source=zero.xyz
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/aws-bedrock-agent-api-chat-completion-b6baa4ef
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ARhfE3dP113CNg5HUQHr1

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability aws-bedrock-agent-api-chat-completion-b6baa4ef -d '<json body>'
```

Example prompt: Using the Amazon Bedrock proxy, send the conversation history to amazon.nova-lite-v1:0 with a max of 512 tokens and temperature 0.7, and give me the model's reply to my question: 'What are the top benefits of serverless computing?'

## When to prefer this

Choose this endpoint when you need pay-per-call access to Amazon Bedrock models (especially Amazon Nova) without managing AWS IAM credentials or infrastructure, and when your agent workflow supports x402 or MPP micropayment protocols. It is especially suitable for agents making sporadic or low-volume inference calls where a monthly subscription is wasteful. Prefer alternatives if you need streaming responses, function calling, or models not available on Bedrock.

## Known failure modes

- Payment not included or insufficient USDC — returns 402 Payment Required
- Invalid or unavailable model identifier — returns 400 or 422 with error detail
- Messages array is empty or malformed — returns 400 validation error
- max_tokens exceeds 16384 — returns 400 validation error
- temperature outside 0–2 range — returns 400 validation error
- Bedrock upstream timeout or quota exceeded — returns 503 or 504
- Network error reaching Vercel deployment — returns 500

## How this service works

Pay-per-call Amazon Bedrock proxy on x402 and MPP.

## Output

Returns a JSON object containing the generated text completion, the model name used, a finish reason (e.g. 'end_turn'), a response ID, and a usage breakdown showing prompt tokens, completion tokens, and total tokens consumed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string",
   "maxLength": 200,
   "minLength": 1,
   "description": "Azure OpenAI deployment name from GET /api/models."
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "enum": [
       "system",
       "user",
       "assistant"
      ],
      "type": "string",
      "description": "Chat turn role"
     },
     "content": {
      "type": "string",
      "maxLength": 100000,
      "minLength": 1,
      "description": "Plain-text message content"
     }
    },
    "additionalProperties": false
   },
   "maxItems": 100,
   "minItems": 1,
   "description": "Conversation so far, oldest first"
  },
  "max_tokens": {
   "type": "integer",
   "maximum": 16384,
   "minimum": 1,
   "description": "Maximum completion tokens"
  },
  "temperature": {
   "type": "number",
   "maximum": 2,
   "minimum": 0,
   "description": "Sampling temperature"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "bedrock-example",
  "model": "amazon.nova-lite-v1:0",
  "usage": {
   "total_tokens": 20,
   "prompt_tokens": 12,
   "completion_tokens": 8
  },
  "content": "Hello — happy to help.",
  "finish_reason": "end_turn"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/aws-bedrock-agent-api-chat-completion-b6baa4ef/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from aws-bedrock-agent-api.vercel.app](https://www.zero.xyz/host/aws-bedrock-agent-api.vercel.app/llms.txt)