# BlockRun.AI LLM Chat Completions Gateway

> BlockRun.AI LLM Chat Completions Gateway is a paid API for AI agents from blockrun-web-vbsbhh7lea-uc.a.run.app, paid per call via x402, $0.028087/call, status unknown (last checked 2026-10-12, last successful call 2026-09-05).

Pay-per-call AI chat completions gateway supporting ChatGPT, Claude, Gemini, DeepSeek, and Grok via x402 micropayments on Base

## Facts

- Endpoint: POST https://blockrun-web-vbsbhh7lea-uc.a.run.app/api/v1/chat/completions?utm_source=zero.xyz
- Price: $0.028087/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Last successful call: 2026-09-05
- Success rate: 97% of calls made through Zero
- Rating: 4.1 / 5 from 5 reviews
- Activations on Zero: 1190
- Tags: x402
- Canonical page: https://www.zero.xyz/c/blockrun-ai-c2a4ec8a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_F5nRpZndzQlTWd097OItB

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 blockrun-ai-c2a4ec8a -d '<json body>'
```

Example prompt: Using the BlockRun pay-as-you-go LLM gateway, send a chat message to gpt-4o-mini asking 'What are the top 3 benefits of renewable energy?' with a temperature of 0.7 and max 300 tokens.

## When to prefer this

Choose this endpoint when you need pay-as-you-go access to multiple major LLMs (OpenAI, Anthropic, Google, DeepSeek, xAI) without subscription commitments, paying only $0.001 USDC per call via x402 on Base. Ideal for agents that need to switch between models dynamically, operate on-chain, or avoid API key management across multiple providers. Prefer this over direct provider APIs when you want unified billing, blockchain-native micropayments, or model flexibility in a single endpoint.

## Known failure modes

- Payment failure: x402 payment not accepted or insufficient USDC balance — returns 402 Payment Required
- Invalid model ID: unsupported or misspelled model identifier — returns 400 Bad Request
- Malformed messages array: missing role or content fields — returns 400 with validation error
- Rate limiting or upstream provider outage — returns 429 or 503
- Temperature out of range (must be 0-2) — returns 400 validation error
- Token limit exceeded for chosen model — returns 400 or truncated response

## How this service works

AI chat completions API - pay per request with USDC on Base

## Output

Returns a chat completion response in OpenAI-compatible format containing the assistant's generated message, the model used, token usage statistics (prompt, completion, total), and finish reason. Response structure mirrors the standard OpenAI chat completions API format.

## Example request

```json
{
 "model": "gpt-4o-mini",
 "stream": false,
 "messages": [
  {
   "role": "user",
   "content": "What are the top 3 benefits of renewable energy?"
  }
 ],
 "max_tokens": 300,
 "temperature": 0.7
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string",
   "description": "AI model ID (e.g., gpt-4o-mini, claude-haiku-4.5)"
  },
  "stream": {
   "type": "boolean",
   "description": "Enable streaming responses"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "role": {
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   },
   "description": "Array of chat messages with role and content"
  },
  "max_tokens": {
   "type": "integer",
   "description": "Maximum tokens to generate"
  },
  "temperature": {
   "type": "number",
   "description": "Sampling temperature (0-2)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/blockrun-ai-c2a4ec8a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from blockrun-web-vbsbhh7lea-uc.a.run.app](https://www.zero.xyz/host/blockrun-web-vbsbhh7lea-uc.a.run.app/llms.txt)