# Surplus Intelligence OpenAI-Compatible Completions

> Surplus Intelligence OpenAI-Compatible Completions is a paid API for AI agents from www.surplusintelligence.ai, paid per call via x402, $0.003302/call, status unknown (last checked 2026-09-14).

Runs text completion inference against a variety of AI models via Surplus Intelligence's OpenAI-compatible legacy completions endpoint, billed per call in USDC.

## Facts

- Endpoint: POST https://www.surplusintelligence.ai/x402/api/inference/v1/completions
- Price: $0.003302/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/www-surplusintelligence-ai-c55a5ffe
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oJvYvpnvGLDGYsBH64Gcs

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 www-surplusintelligence-ai-c55a5ffe -d '<json body>'
```

Example prompt: Using Surplus Intelligence's completions endpoint, run a text completion with the model 'gpt-3.5-turbo-instruct', prompt 'Once upon a time in a futuristic city', max 200 tokens, and temperature 0.7.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible legacy text completions (not chat completions), want per-call USDC micropayment billing without a subscription, or need to access a variety of models through a single compatible interface at market prices.

## Known failure modes

- Invalid or unavailable model ID returns an error — call /x402/api/inference/v1/models to list valid models
- Insufficient USDC payment results in 402 Payment Required
- Prompt exceeds model context window returns a token limit error
- Temperature out of range (0–2) causes a validation error
- Missing required 'model' or 'prompt' fields returns a 400 Bad Request

## How this service works

Buy the cheapest inference. Sell your credits. The open order book for AI models. Up to 90% off GPT-5.5, Claude Opus 4.8, and more.

## Output

Returns an OpenAI-compatible completions response containing the generated text continuation(s) for the given prompt, using the specified model and sampling parameters.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string",
   "description": "Surplus Intelligence model id. Call /x402/api/inference/v1/models for available models."
  },
  "prompt": {
   "oneOf": [
    {
     "type": "string"
    },
    {
     "type": "array",
     "items": {
      "type": "string"
     }
    }
   ],
   "description": "OpenAI-compatible legacy completion prompt."
  },
  "stream": {
   "type": "boolean"
  },
  "max_tokens": {
   "type": "integer",
   "minimum": 1,
   "description": "Maximum output tokens."
  },
  "temperature": {
   "type": "number",
   "maximum": 2,
   "minimum": 0
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "cmpl_surplus_example",
  "usage": {
   "total_tokens": 14,
   "prompt_tokens": 8,
   "completion_tokens": 6
  },
  "object": "text_completion",
  "choices": [
   {
    "text": "Hello from Surplus Intelligence.",
    "index": 0,
    "finish_reason": "stop"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/www-surplusintelligence-ai-c55a5ffe/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from www.surplusintelligence.ai](https://www.zero.xyz/host/www.surplusintelligence.ai/llms.txt)