# Omnicall LLM Gateway — OpenAI-Compatible Multi-Model Router

> Omnicall LLM Gateway — OpenAI-Compatible Multi-Model Router is a paid API for AI agents from gateway.gocreativeai.com, paid per call via x402, $0.003/call, status down (last checked 2026-09-16).

Routes requests to 240+ frontier LLMs (GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen) via a single OpenAI-compatible endpoint, billed per call in USDC on Base or Solana

## Facts

- Endpoint: GET https://gateway.gocreativeai.com/v1/defi/%7Barg%7D
- Price: $0.003/call
- Payment: x402
- Status: down
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/omnicall-llm-gateway-openai-compatible-multi-model-router-bf042185
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_M6haxk7J8pWKvACjSZtCF

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 omnicall-llm-gateway-openai-compatible-multi-model-router-bf042185
```

Example prompt: Call Claude 3.5 Sonnet through the Omnicall gateway and ask it to summarize the following article in 3 bullet points, paying per call with USDC on Base — no API key needed.

## When to prefer this

Choose this endpoint when you need to call multiple different LLMs without managing separate API keys or subscriptions, want to pay per-call in USDC rather than commit to a monthly plan, are building an agent on Base or Solana that needs on-chain micropayments for AI inference, or need to switch between frontier models (GPT, Claude, Gemini, DeepSeek, etc.) using a single OpenAI-compatible SDK.

## Known failure modes

- Insufficient USDC balance — payment rejected before inference runs
- Invalid or unsupported model name in the request body
- Malformed messages array not conforming to OpenAI chat format
- Upstream model provider outage causing 502 or timeout
- Rate limiting or capacity errors from the underlying model provider
- Invalid DeFi payment signature or unsupported chain
- Request body missing required 'model' or 'messages' fields

## How this service works

Omnicall routes 240+ frontier models (GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen) through one OpenAI-compatible endpoint. Pay per call in USDC on Base or Solana — no API key, no subscription, no rate limits.

## Output

An OpenAI-compatible chat completion response containing the model's generated text, finish reason, and token usage counts, returned from whichever frontier model was specified in the request.

## 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"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "pathParams": {
     "type": "object"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "input"
     ],
     "properties": {
      "input": {
       "type": "string",
       "description": "endpoint argument"
      }
     }
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/omnicall-llm-gateway-openai-compatible-multi-model-router-bf042185/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gateway.gocreativeai.com](https://www.zero.xyz/host/gateway.gocreativeai.com/llms.txt)