# NetIntel API – AI Chat Completion (MCP/Messages)

> NetIntel API – AI Chat Completion (MCP/Messages) is a paid API for AI agents from netintel-production-440c.up.railway.app, paid per call via x402, $0.06/call, status unknown (last checked 2026-09-14, last successful call 2026-07-17).

Processes natural language chat messages via an OpenAI-compatible chat completion interface, returning AI-generated responses with token usage stats, paid per-call via x402 micropayments in USDC on Base.

## Facts

- Endpoint: POST https://netintel-production-440c.up.railway.app/messages
- Price: $0.06/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Last successful call: 2026-07-17
- Success rate: 100% of calls made through Zero
- Rating: 4.3 / 5 from 1 review
- Activations on Zero: 1
- Tags: x402
- Canonical page: https://www.zero.xyz/c/netintel-api-ai-chat-completion-mcp-messages-0ffa051f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AC7TVXB97Vn4zTvJGqmjQ

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 netintel-api-ai-chat-completion-mcp-messages-0ffa051f -d '<json body>'
```

Example prompt: Ask the NetIntel AI chat endpoint 'What is the capital of France?' and give me back the assistant's reply along with how many tokens were used — pay the per-call fee in USDC automatically.

## When to prefer this

Choose this endpoint when you need a pay-per-call AI chat completion with no signup, no API keys, and automatic no-charge on failed calls. Ideal for agents that want to query Claude on-demand using USDC micropayments on Base mainnet via x402, especially in agentic pipelines where predictable per-call billing and zero-friction onboarding matter. Prefer over traditional OpenAI/Anthropic direct APIs when you need crypto-native payment rails without subscription overhead.

## Known failure modes

- Input validation rejection — returns error without charge if message format is invalid
- Upstream model failure — no charge on server or provider errors
- Payment failure — x402 micropayment not completed, request not processed
- Malformed request body — missing required messages field
- Rate or quota issues on upstream Claude provider

## How this service works

Network intelligence API — 138 endpoints, all pay-per-call via x402 micropayments (USDC on Base or Solana mainnet).

NetIntel is agent fair-trade aligned: transparent per-call pricing in USDC on Base or Solana via x402, no API keys or signup, and automatic no-charge on server errors, upstream failures, and input-validation rejections — failed calls are never billed across NetIntel's network, domain, and data-intelligence endpoints.

## Output

Returns an OpenAI-compatible chat completion JSON object containing: the assistant's reply text inside choices[0].message.content, a finish_reason ('stop'), the model used (claude-sonnet-4-6), token usage breakdown (prompt_tokens, completion_tokens, total_tokens), a unique completion ID, and a Unix timestamp. No streaming — single synchronous response.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "required": [
      "messages"
     ],
     "properties": {
      "model": {
       "type": "string",
       "description": "Model to use. Supported: claude-sonnet-4-6 (aliases: balanced, sonnet). Optional — defaults to claude-sonnet-4-6."
      },
      "top_p": {
       "type": "number",
       "description": "Nucleus sampling (0–1). Optional; ignored if temperature is set."
      },
      "messages": {
       "type": "array",
       "items": {
        "type": "object",
        "required": [
         "role",
         "content"
        ],
        "properties": {
         "role": {
          "type": "string",
          "description": "system, user, or assistant"
         },
         "content": {
          "type": "string",
          "description": "Message text"
         }
        }
       },
       "description": "Chat messages in OpenAI format. Each item is {role: 'system'|'user'|'assistant', content: string}. System messages are applied as the system prompt."
      },
      "max_tokens": {
       "type": "number",
       "description": "Maximum output tokens. Optional — defaults to 1024, capped at 1024."
      },
      "temperature": {
       "type": "number",
       "description": "Sampling temperature (0–1). Optional."
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "id": {
       "type": "string"
      },
      "model": {
       "type": "string"
      },
      "usage": {
       "type": "object",
       "description": "prompt_tokens, completion_tokens, total_tokens"
      },
      "object": {
       "type": "string",
       "description": "Always 'chat.completion'"
      },
      "choices": {
       "type": "array",
       "description": "One choice with the assistant message and a finish_re
… (truncated)
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "chatcmpl-abc123",
  "model": "claude-sonnet-4-6",
  "usage": {
   "total_tokens": 22,
   "prompt_tokens": 14,
   "completion_tokens": 8
  },
  "object": "chat.completion",
  "choices": [
   {
    "index": 0,
    "message": {
     "role": "assistant",
     "content": "The capital of France is Paris."
    },
    "finish_reason": "stop"
   }
  ],
  "created": 1735689600
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/netintel-api-ai-chat-completion-mcp-messages-0ffa051f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from netintel-production-440c.up.railway.app](https://www.zero.xyz/host/netintel-production-440c.up.railway.app/llms.txt)