Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware…
Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware - your data is never forwarded to OpenAI/Anthropic or any third-party LLM cloud. OpenAI-compatible chat completions: summarize, draft, extract, translate, code, answer ques…
by api.erb-llm.com · discovered, not yet claimed by its owner · updated 2026-10-11
Mirrored from Coinbase's public x402 Bazaar. The description is the provider's own text and has not been reviewed here; the payment requirements are copied as published.
What it does
Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware - your data is never forwarded to OpenAI/Anthropic or any third-party LLM cloud. OpenAI-compatible chat completions: summarize, draft, extract, translate, code, answer questions. Send a messages array, get chat.completion JSON. Pay per call in USDC on Base (x402), no API key or account. Tiers by output cap: quick 4,096 / long 8,192 / extended 32,768 tokens. Free trial: POST /v1/trial.
Tags: llm · chat · inference · private · openai-compatible · bazaar
Call contract
- Method
- POST
- Input
- json
- Output
- json
- Last paid call
- 2026-10-11
{
"messages": [
{
"content": "You are a helpful assistant.",
"role": "system"
},
{
"content": "Reply with exactly one word: hello",
"role": "user"
}
],
"model": "qwen/qwen3.8-27b",
"temperature": 0.2
}{
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "hello",
"role": "assistant"
}
}
],
"id": "chatcmpl-abc123",
"model": "qwen/qwen3.8-27b",
"object": "chat.completion",
"usage": {
"completion_tokens": 1,
"prompt_tokens": 30,
"total_tokens": 31
},
"x402": {
"charged": "$0.001",
"inference_ms": 1830,
"output_cap": 4096,
"tier": "quick",
"tokens_out": 1
}
}Use with an agent
- Discover. Agents find this listing with
GET https://bazaar.saylorinnovations.com/discovery/search?query=…, the MCP toolsearch_resources, or/discovery/resources. - Inspect. Fetch
/resources/35603.jsonfor the price and payment options. - Pay. Call
GET https://api.erb-llm.com/v1/chat/completions. The provider answers402with its payment requirements. An x402 client signs one of the options below and retries withPAYMENT-SIGNATURE. - Execute. The provider returns
200with the data. Agent Bazaar is not in the request path and never sees your payment.
For humans
You don't need an account or an API key; you need a wallet holding a small amount of USDC on Base, and an x402-capable client (see the examples below). Call the endpoint unpaid first to see exactly what it asks for.
Pricing & payment
- Price
- $0.001 / request
- Protocol
- x402 v2
- Auth
- No account or API key. Pay per request.
- Networks
- Base
- Demand
- 20 calls · 4 unique payers in 30d (public x402 Bazaar data)
x402 payment requirements
| Scheme | Network | Asset | Amount | Pay to | Timeout |
|---|---|---|---|---|---|
| exact | Base eip155:8453 | USDC | $0.001 | 0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8 | 300s |
accepts[] (raw JSON)
[
{
"scheme": "exact",
"network": "eip155:8453",
"payTo": "0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "1000",
"amountUsd": 0.001,
"maxTimeoutSeconds": 300
}
]Schemas
Output schema (JSON Schema)
{
"properties": {
"example": {
"properties": {
"choices": {
"items": {
"properties": {
"finish_reason": {
"type": "string"
},
"index": {
"type": "integer"
},
"message": {
"properties": {
"content": {
"type": "string"
},
"role": {
"type": "string"
}
},
"type": "object"
}
},
"type": "object"
},
"type": "array"
},
"id": {
"type": "string"
},
"model": {
"type": "string"
},
"object": {
"const": "chat.completion"
},
"usage": {
"properties": {
"completion_tokens": {
"type": "integer"
},
"prompt_tokens": {
"type": "integer"
},
"total_tokens": {
"type": "integer"
}
},
"type": "object"
},
"x402": {
"description": "Billing stamp added by the gateway.",
"properties": {
"capped_from": {
"type": "integer"
},
"charged": {
"type": "string"
},
"inference_ms": {
"type": "integer"
},
"note": {
"type": "string"
},
"output_cap": {
"type": "integer"
},
"tier": {
"type": "string"
},
"tokens_out": {
"type": "integer"
}
},
"type": "object"
}
},
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}Example shape — generated from the schema, not a captured live response
{
"example": {
"choices": [
{
"finish_reason": "string",
"index": 0,
"message": {
"content": "string",
"role": "string"
}
}
],
"id": "string",
"model": "string",
"object": null,
"usage": {
"completion_tokens": 0,
"prompt_tokens": 0,
"total_tokens": 0
},
"x402": {
"capped_from": 0,
"charged": "string",
"inference_ms": 0,
"note": "string",
"output_cap": 0,
"tier": "string",
"tokens_out": 0
}
},
"type": "string"
}Examples
curl "https://api.erb-llm.com/v1/chat/completions"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paidconst res = await fetch("https://api.erb-llm.com/v1/chat/completions");
if (res.status === 402) {
const { accepts } = await res.json();
// pay one of accepts[] via an x402 client, then retry with the payment header
}import httpx
res = httpx.get("https://api.erb-llm.com/v1/chat/completions")
if res.status_code == 402:
accepts = res.json()["accepts"]
# pay one of accepts[] via an x402 client, then retry with the payment headerDetails
- Provider
- api.erb-llm.com
- Endpoint
- https://api.erb-llm.com/v1/chat/completions
- Machine-readable
/resources/35603.json