European open-weight models. Mistral Large for complex tasks, Mistral Small for speed, Codestral for code. Strong multilingual support. Open and API options.
Mistral is a French AI company producing high-quality open-weight models. Mistral Large is the general-purpose model for reasoning and complex tasks. Mistral Small is optimized for low-latency applications where speed matters more than peak capability. Codestral is their code-specialized model with fill-in-the-middle support for autocomplete. All models have strong multilingual performance, particularly for European languages. Mistral pioneered the sliding window attention and mixture-of-experts techniques that are now industry standard. You can access models through the Mistral API and its Mistral Studio console (formerly La Plateforme), download open weights for self-hosting, or use them via OpenRouter and other gateways. For European companies with data sovereignty requirements, Mistral is the natural choice.
Last verified
curl -LsSf https://mistral.ai/vibe/install.sh | bashpip install mistralaiSources: Mistral pricing, Mistral docs changelog, Vibe CLI install and setup, Mistral SDKs
Anthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.
Chinese lab shipping open-weight MoE models. The V4 family (previewed April 24, 2026) runs a 1M context on DeepSeek's API; R1 (2025) popularized open reasoning models. Low-cost API.
OpenAI's GPT-5 model, released August 2025. Unified fast and reasoning modes in one model. Superseded by the GPT-6 family in September 2026 and now marked deprecated in the API.
Google's model family. As of October 2026 Gemini 4 Argon (GA October 13, 1M token context) is the flagship for coding and agents, with Gemini 3.8 Flash (free tier in AI Studio) as the fast, cheaper option.
European open-weight models. Mistral Large for complex tasks, Mistral Small for speed, Codestral for code. Strong multilingual support. Open and API options.
Try MistralHonest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeAnthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.
OpenAI's chat app. As of October 2026 Free and Go run GPT-6 Luna; Plus ($20/mo) adds GPT-6.1 Sol and GPT-6 Astra. Agent mode, Codex, image generation, code interpreter.
Unified API for hundreds of models. One API key, one billing dashboard. OpenAI, Anthropic, Google, Meta, Mistral, and more. Automatic fallbacks and load balancing.
Install Ollama and LM Studio, pull your first model, and run AI locally for coding, chat, and automation - with zero cloud dependency.
Getting StartedUse opus, sonnet, haiku, and best to switch models easily.
Claude CodeInstall the dd CLI and scaffold your first AI-powered app in under a minute: Next.js 16, Convex, Clerk, Autumn, Tailwind v4 and an agent-ready CLAUDE.md.
Getting Started
Ornith-1.0 open-source coding models explained: what "self-improving" really means, the four model sizes, hardware needs...

Qwen3.6-27B is the local coding model to benchmark first: what hardware it needs, which jobs it should take over, and wh...

State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5....

Cursor 2.0 ships Composer, the first in-house Cursor coding model, and a multi-agent interface. How Composer was trained...

Kimi K2 from Moonshot AI replaced Claude Sonnet 4 in my stack - an open-source 1T-parameter MoE model that is faster, ch...

Grok Code Fast 1 is xAI's speed-optimized coding model for agentic workflows. See its pricing, where to use it, and how...

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.