# 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, $0.25/call, status down (last checked 2026-09-15).

Routes inference requests to 240+ frontier LLMs (GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen) via a single OpenAI-compatible endpoint, paid per call in USDC with no API key required.

## Facts

- Endpoint: GET https://gateway.gocreativeai.com/v1/ai/ultra/%7Barg%7D
- Price: $0.25/call
- Payment: x402
- Status: down
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/omnicall-llm-gateway-openai-compatible-multi-model-router-2cd015aa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Y69Yri-w5qaTa7lYEVDOB

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-2cd015aa
```

Example prompt: Send a chat completion request to the Omnicall gateway using Claude 3.5 Sonnet — the message is 'Summarize the pros and cons of nuclear energy in 3 bullet points' — and pay per call in USDC, no API key needed.

## When to prefer this

Prefer this endpoint when you need to access multiple frontier LLMs without managing separate API keys or subscriptions, especially in crypto-native or autonomous agent contexts where paying per call in USDC on Base or Solana is preferred over monthly billing. Ideal for AI agents that need flexible model routing across GPT, Claude, Gemini, Grok, DeepSeek, Llama, and Qwen through a single OpenAI-compatible interface.

## Known failure modes

- Insufficient USDC balance or failed on-chain payment results in HTTP 402 Payment Required
- Invalid or unsupported model identifier in the {arg} path parameter returns a 400 or 404 error
- Malformed request body (non-OpenAI-compatible format) returns a 422 Unprocessable Entity
- Upstream model provider outage causes timeouts or 503 errors
- Rate limits from upstream providers may still cause occasional 429 errors despite gateway claims

## 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

Returns an OpenAI-compatible chat completion response object containing the generated text, model used, token usage statistics, and finish reason — formatted identically to the OpenAI Chat Completions API response schema.

## 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-2cd015aa/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)