llm402.ai — LLM Inference (40+ models)

L402 New ai degraded

P50 Latency 381ms

Uptime 100.0%

Price Paid

OpenAI-compatible chat completions with intelligent auto-routing. 40+ models including DeepSeek R1, Kimi K2.5, Qwen3.5, GLM-5, Llama, Mistral. Pay per request via Lightning. Supports streaming, buffered, and prepaid balance tokens.

Score Breakdown

Intermittent Fast Stable pricing

30-Day Trends

Uptime

Latency

No price data — endpoint has not responded successfully.

Endpoint Details

URL

https://llm402.ai/v1/chat/completions

Canonical URL https://llm402.ai/v1/chat/completions

Sources 402index

Last Scan Mar 31

Scan Cycles 1

Consecutive Failures 2

P99 Latency: 381ms

Quick Start

Use with an Agent

1. Install MCP server

claude mcp add boltzpay -- npx -y @boltzpay/mcp

Paste in your terminal

2. Ask your agent

Fetch https://llm402.ai/v1/chat/completions and return the result

Use in Code

CLI

npx boltzpay fetch "https://llm402.ai/v1/chat/completions"

SDK Documentation