Blog

Technical articles on inference optimization and building with LLMs.

Use Auriko with Hermes Agent, OpenClaw, and Kilo Code

Auriko works as a provider in all three. One API key, models from Anthropic, DeepSeek, Google, and others.

Use the Response API with DeepSeek, Gemini, Claude, and every model on Auriko

The Response API format works across all 250+ models on Auriko, with streaming, tool calling, and multi-model routing.

Use DeepSeek, Kimi, GLM, and other open-source models in Claude Code with Auriko

Point Claude Code at Auriko to access open-source and open-weight models through one API key.

Use DeepSeek, Gemini, Grok, and 250+ models in OpenCode with Auriko

Auriko is a registered provider in OpenCode. One environment variable, 15 models out of the box, 250+ with a config line.

The variables that affect your inference cost

How provider caching mechanics interact with your workload to determine inference cost, and how to optimize for it.