Blog
Hướng dẫn và ghi chú về API mô hình chi phí thấp cho AI agent.
Chưa có bài viết bằng ngôn ngữ này. Dưới đây là các bản gốc đã xuất bản bằng ngôn ngữ khác.
Your Relay's Status Page Says 100% - Here's What It Is Actually Measuring
Why a green status page may not describe your model request: check monitoring scope, completed outcomes, routing evidence, sample size and measurement limits.
Retry vs Fallback vs Failover - the Difference That Decides Your Bill
Three words used interchangeably, three completely different cost and quality outcomes. A 30-second definition table, where each one breaks, and which to use for agent loops, batch and chat.
80% of Your Requests Time Out and Failover Never Fires - a Diagnostic Order
When most of your LLM requests time out but failover supposedly handles it, find the real failing layer: client, network, relay, upstream - and the three numbers to collect at each.
How to Tell If Your LLM API Relay's Failover Is Real
How to check a relay with a controlled failure, response data and a request trace—and why status codes, model names and latency alone cannot prove failover.
Particle-1 API: Pricing, Benchmarks vs DeepSeek V4.1 Flash
Particle-1 API guide: official price ($0.25/$1.00 per 1M), OpenRouter's lower listing, 1M context, vendor benchmarks vs DeepSeek V4.1 Flash, and how to call it.

Kimi K3.1 Pro API: Pricing, 1M Context, How to Call It
Kimi K3.1 Pro API pricing checked against Moonshot: $2/$10 per 1M tokens, 1M context, Highspeed, how to call it, plus Flint as a free coding fallback.

GPT-6.1 Terra API: Pricing, Batch and How to Call It
GPT-6.1 Terra API pricing checked against OpenAI: $1/$5 per 1M tokens, the 272K long-context rule, 50% batch, 1.05M context, and code to call it.

tstack on a Budget: Claude Code Skills, One Cheap Key
Run Theo's tstack skills in Claude Code or Codex on one cheap API key: custom base URL setup, which model group per skill, and why council and sol-loop differ.

Free LLM API Options in 2026: Limits Checked
Which LLM APIs are still free? We checked OpenRouter, Gemini, Groq, Mistral, Cloudflare, SambaNova and Cerebras docs: real limits, cards, gotchas.