Models
Releases, benchmarks and what changed.
Mistral Large 4 Opens Its Weights: What Changes
Mistral Large 4 weights are available. See what changed since preview, current API prices, reasoning modes, license terms, and self-hosting choices.
Context windows explained: how much fits in 128K, 256K and 1M tokens
A 128K-token context window holds about 77,000 to 102,000 English words. What a context window is, the windows of current models, and why the answer needs room too.
How much VRAM do you need to run an LLM locally?
VRAM needed for 8B, 14B, 32B, 70B and 120B models at F16, Q8 and Q4, worked out from each model's official config, plus what memory bandwidth says about speed.
AI API prices per million tokens, compared (October 2026)
Input, cached and output prices per million tokens for GPT-6, Claude 5, Gemini 4, DeepSeek V4, Grok and Mistral models, from each provider's own pricing page.
How many tokens is 1,000 words? A practical guide to tokens
1,000 English words are about 1,250 to 1,670 tokens. How tokens work, why code and other languages use more, and how to count your own text exactly.