AI Models
Overview of AI models and local runtimes for AI agents.
AI Models(415)
Current overview of AI models — pricing, context and focus.
Anthropic: Claude Haiku 5.5
Anthropic
Anthropic: Claude Haiku 5.5 (batch)
Anthropic
Google: Gemini 4 Argon
Google: Gemini 4 Argon (batch)
Google: Nano Banana 2.1
Meta: Muse Spark Open
Meta
Meta: Muse Wonder
Meta
MiniMax: MiniMax M3.1 Flash
MiniMax
Mistral: Mistral Large 4
Mistral
MoonshotAI: Kimi K3.1 Pro
MoonshotAI
NVIDIA: Nemotron 3.5 Super VL
NVIDIA
Anthropic: Claude Fable 5.1
Anthropic
Anthropic: Claude Fable 5.1 (batch)
Anthropic
Anthropic: Claude Opus 5.5
Anthropic
Anthropic: Claude Opus 5.5 (batch)
Anthropic
Anthropic: Claude Sonnet 5.5
Anthropic
Anthropic: Claude Sonnet 5.5 (batch)
Anthropic
DeepSeek: DeepSeek Flash Latest
DeepSeek
DeepSeek: DeepSeek Pro Latest
DeepSeek
DeepSeek: DeepSeek V4.1 Flash
DeepSeek
DeepSeek: DeepSeek V4.1 Flash (batch)
DeepSeek
Google: Gemini 3.8 Flash
Google: Gemini 3.8 Flash (batch)
Meta: Muse Spark 1.3
Meta
Meta: Muse Spark 1.3 Contributor
Meta
NVIDIA: Switchyard
NVIDIA
OpenAI: GPT Astra Latest
OpenAI
OpenAI: GPT Luna Latest
OpenAI
OpenAI: GPT Sol Latest
OpenAI
OpenAI: GPT Terra Latest
OpenAI
Data updated: 10/26/2026 · Prices are indicative, per 1M input tokens, based on public price lists. The provider's official pricing applies.
Local AI Runtimes
Install a runtime first, then download models into it to run AILoft agents locally.
Ollama
Run LLMs locally. Supports Llama, Gemma, Phi, Mistral and more.
LM Studio
Desktop app for running local LLMs with GUI. GGUF model support.
Jan.ai
Open-source ChatGPT alternative that runs offline on your computer.
GPT4All
Free, local, privacy-aware chatbot. No GPU required.
AnythingLLM
All-in-one AI app with RAG, agents, and multi-model support.
text-generation-webui
Gradio web UI for running large language models locally.
Looking for GPU power to run models locally or self-host inference?
GPU servers →