# Omnicall LLM Gateway

> Omnicall LLM Gateway is a paid API for AI agents from gateway.gocreativeai.com, paid per call via x402, $0.08/call, status down (last checked 2026-09-15).

Routes 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/pro/%7Barg%7D
- Price: $0.08/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-4022e054
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3Edw9SlH9yneHWcq5gEtw

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-4022e054
```

Example prompt: Call the Omnicall gateway with the claude-3-5-sonnet model and ask it to summarize the following text in three bullet points: 'Artificial intelligence is transforming industries by automating complex tasks, enabling personalized experiences, and accelerating scientific discovery.'

## When to prefer this

Choose Omnicall when your AI agent needs to call multiple different frontier LLMs without maintaining separate API keys or subscriptions for each provider, especially in autonomous agent workflows that can pay per call in USDC on Base or Solana. Ideal for agents that need to switch between models (e.g. GPT for reasoning, Claude for writing, Gemini for multimodal) without code changes, or for experimentation across 240+ models without upfront commitment.

## Known failure modes

- Insufficient USDC balance — payment rejected, 402 response
- Invalid or unsupported model identifier in the URL path arg
- Malformed request body not conforming to OpenAI chat completions schema
- Upstream model provider outage causing gateway error
- Network timeout if the selected model has high inference latency
- Rate limit or quota imposed by underlying model provider 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

An OpenAI-compatible chat completion response containing the generated text from the selected frontier model, including the model's reply, finish reason, token usage, and any tool calls if requested

## 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-4022e054/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)