Skip to content

Private LLM Inference - Long · api.erb-llm.com

Privacy-first long-form inference

8,192-token output cap on a local open-weight model on dedicated hardware - prompts never reach OpenAI/Anthropic or any third-party cloud. OpenAI-compatible chat completions (messages array in, chat.completion JSON out) for summarization, drafting, extraction, translation, code, multi-paragraph answers. Pay per call in USDC on Base (x402), no API key or account. Shorter work? Use the cheaper quick tier (4,096 tokens).

Ready now8 calls · 4 buyers in 30 days

Input

Optional output token ceiling. This tier caps output at 8192 tokens - higher values are clamped to 8192, not rejected. Use the long/extended tiers for bigger outputs.
Messages
OpenAI chat messages (system/user/assistant).
messages-1
messages-2
Optional. The server runs one pinned model; any value is accepted but the pinned model serves the call.

Sample response

Published by the provider. Your run returns a fresh response.

response6 keys
choices1 item
id"chatcmpl-abc123"
model"qwen/qwen3.8-27b"
object"chat.completion"
usage3 keys
completion_tokens1
prompt_tokens30
total_tokens31
x4025 keys
charged"$0.01"
inference_ms1830
output_cap8192
tier"long"
tokens_out1
responseobject, 6 keys
Your agent can do this on its own
Add the MCP URL in Claude Code, Cursor or Codex. Your agent can run Tools within its spending limits, or ask for approval each time. Connect your agent

Connect your agent

Add one MCP URL and your agent can find and run this tool within its spending limits. Choose “Ask each time” if you want to approve every Call.

MCP URL

https://app.aecon.ai/mcp
Terminalbash
claude mcp add --transport http --scope user agentic-economy "https://app.aecon.ai/mcp"

In Claude Code, open /mcp, select agentic-economy, then choose Authenticate.

Track record

Paid calls, last 30 days
8
Buyers, last 30 days
4
Last paid call

Reported by the x402 directory.

A$0.015 per call