Start free trial
Blog

Stories from the gateway

Models

Kimi K3 vs MiniMax M3: The Top and the Floor

One is the strongest open-weight model available. The other is among the cheapest capable ones and natively multimodal. The gap between them is a budget decision.

· 8 min read
Models

Kimi K3 vs Qwen 3.6: A Cluster or a Single GPU

K3 needs roughly 1.6TB of weights and multi-node serving. Qwen 3.6 27B is dense and fits on one accelerator. The comparison is about deployment, not benchmarks.

· 8 min read
Fundamentals

KV Cache Explained: The Memory Behind Long Context

· 8 min read
Models

Latency-Adjusted Model Scoring: When Fast Beats Smart

· 9 min read
Fundamentals

Layer Normalisation: The Part That Keeps Training Stable

· 8 min read
Guides

LlamaIndex Setup on a Custom OpenAI-Compatible Endpoint

· 9 min read
Guides

LLM Classification: Fix the Taxonomy Before the Model

· 9 min read
Guides

LLM Data Extraction: Design the Schema Before the Prompt

· 9 min read
Guides

LLM Summarisation: Omission Hurts More Than Invention

· 9 min read
Guides

LLM Translation: Placeholders, Glossaries and Register

· 9 min read
Guides

LLM-Powered Search: The Model Is Not the Retriever

· 9 min read
Fundamentals

Load Balancing in MoE: Stopping Experts Going Idle

· 9 min read
Guides

Logging LLM Requests Safely Without Building a Liability

· 9 min read
Fundamentals

Logits and Softmax: What a Model Really Outputs

· 8 min read

Ready to start?

Every model, one key. Start free and upgrade when you are ready.

Start free trialSee pricing