Official rows
Pricing pages use provider-owned pricing sources, then separate input, output, cache, batch, image, video, and audio billing units.
AI model decision index
Composite AI Model Rankings. API Prices. Local LLM Match.
Start with the decision you need to make. AI Jupyter connects ranking evidence, official API prices, local hardware fit, and provider changes into practical model shortlists.
Evidence engine
Not a generic AI list. A model-selection evidence map.
AI Jupyter is built around decisions a builder actually has to make: which model to test, what the API bill might become, whether a local setup will feel usable, and which provider changes deserve a fresh comparison.
Public benchmark mix
Ranking pages blend task-specific public leaderboard signals and show source coverage instead of treating missing rows as zero.
Hardware constraints
Local model pages start from RAM, VRAM, quantization, runtime, and real comfort limits before recommending a model.
Official-source radar
AI Radar checks provider-owned changelogs, docs, blogs, pricing pages, and model pages, then summarizes only decision-relevant changes.
Composite Top 5
Rankings by use case
Best AI for Coding
Best AI for Coding
Composite #1
Claude Fable 5
1
Claude Fable 5
Anthropic
99.9
Composite
2
Claude Opus 4.8
Anthropic
92.7
Composite
3
Claude Opus 4.7 Thinking
Anthropic
89.9
Composite
4
Claude Opus 4.8 Thinking
Anthropic
89.9
Composite
5
Claude Opus 4.7
Anthropic
89.9
Composite
Best AI for Writing
Best AI for Writing
Composite #1
Claude Fable 5
1
Claude Fable 5
Anthropic
97.4
Composite
2
Google
Gemini 3 Pro
97.1
Composite
3
Claude Opus 4.7 Thinking
Anthropic
96.7
Composite
4
Claude Opus 4.6 Thinking
Anthropic
96.2
Composite
5
Claude Opus 4.7
Anthropic
96.1
Composite
Best AI for Math
Best AI for Math
Composite #1
Claude Fable 5
1
Claude Fable 5
Anthropic
95.9
Composite
2Google
Gemini 3.5 Flash
91.2
Composite
3
Claude Opus 4.6 Thinking
Anthropic
91.2
Composite
4
GPT-5.4 High
OpenAI
90.5
Composite
5
Claude Opus 4.6
Anthropic
90.5
Composite
Best AI for Image Generation
Best AI for Image Generation
Composite #1
GPT Image 2
1
GPT Image 2
OpenAI
100
Composite
2Google
Nano Banana 2 / Gemini 3.1 Flash Image Preview
92.4
Composite
3
GPT Image 1.5 High Fidelity
OpenAI
92.3
Composite
4
HiDream-O1-Image-1.5
HiDream
91.3
Composite
5
Reve 2.0
Reve
90.2
Composite
Best AI for Writing Essays
Best AI for Writing Essays
Composite #1
Claude Fable 5
1
Claude Fable 5
Anthropic
96.1
Composite
2Google
Gemini 3 Pro
95.9
Composite
3
Claude Opus 4.6 Thinking
Anthropic
95.3
Composite
4
Claude Opus 4.7 Thinking
Anthropic
94.9
Composite
5
Claude Opus 4.7
Anthropic
94.3
Composite
Official API costs
API price explorer
Categories
4
Text
Text APIs
Chat, reasoning, coding, agents, RAG, extraction, and long-context text workloads.
Cost per 1,000 runs
Chat, coding, agents, RAG
Images
Image APIs
Text-to-image, image editing, native image generation, and production image pipelines.
Cost per image
Generation, editing, product media
Video
Video APIs
Text-to-video, image-to-video, video-to-video, editing, reframe, and ad-creative workloads.
Cost per clip
Ads, social clips, creative testing
Audio
Audio APIs
Text-to-speech, speech-to-text, realtime voice agents, translation, dubbing, and sound workflows.
Cost by audio unit
TTS, STT, realtime voice
Hardware match
Local LLM match
Hardware guides
24
8 GB RAM laptop
Best Local LLMs for 8GB RAM in 2026: Ollama, LM Studio, and Model Picks
Practical local LLM picks for 8GB laptops and CPU-only machines.
8 GB RAMNo GPU
16 GB RAM machine
Best Local LLMs for 16GB RAM in 2026: Ollama and LM Studio Picks
Balanced local LLMs for 16 GB laptops and MacBooks.
16 GB RAMNo GPU
32 GB RAM desktop
Best Local LLMs for 32GB RAM in 2026: 7B, 8B, and 14B Picks
Stronger local LLMs for 32 GB RAM systems.
32 GB RAMNo GPU
RTX 5090 workstation
Best Local LLMs for RTX 5090 in 2026: 32 GB VRAM Picks
Top-end single-GPU local LLM picks for 32 GB VRAM RTX 5090 builds.
64 GB RAM32 GB VRAM
RTX 5080 workstation
Best Local LLMs for RTX 5080 in 2026: 16 GB VRAM Picks
Practical local LLM picks for 16 GB VRAM RTX 5080 systems.
64 GB RAM16 GB VRAM
RTX 5070 Ti workstation
Best Local LLMs for RTX 5070 Ti in 2026: 16 GB VRAM Picks
Balanced 16 GB VRAM local LLM picks for RTX 5070 Ti machines.
64 GB RAM16 GB VRAM
RTX 5070 workstation
Best Local LLMs for RTX 5070 in 2026: 12 GB VRAM Picks
12 GB VRAM local LLM picks for RTX 5070 desktop builds.
32 GB RAM12 GB VRAM
RTX 5060 Ti 16GB workstation
Best Local LLMs for RTX 5060 Ti 16GB in 2026: 16 GB VRAM Picks
16 GB VRAM local LLM picks for RTX 5060 Ti 16GB systems.
32 GB RAM16 GB VRAM
RTX 5060 Ti 8GB workstation
Best Local LLMs for RTX 5060 Ti 8GB in 2026: 8 GB VRAM Picks
8 GB VRAM local LLM picks for RTX 5060 Ti 8GB systems.
32 GB RAM8 GB VRAM
RTX 5060 workstation
Best Local LLMs for RTX 5060 in 2026: 8 GB VRAM Picks
8 GB VRAM local LLM picks for RTX 5060 systems.
32 GB RAM8 GB VRAM
RTX 4090 workstation
Best Local LLMs for RTX 4090 in 2026: 24GB VRAM Picks
High-performance local LLMs for 24 GB VRAM RTX 4090 builds.
64 GB RAM24 GB VRAM
RTX 4080 workstation
Best Local LLMs for RTX 4080 in 2026: 16 GB VRAM Picks
16 GB VRAM local LLM picks for RTX 4080 and RTX 4080 Super systems.
64 GB RAM16 GB VRAM
RTX 4070 Ti Super workstation
Best Local LLMs for RTX 4070 Ti Super in 2026: 16 GB VRAM Picks
16 GB VRAM local LLM picks for RTX 4070 Ti Super desktops.
64 GB RAM16 GB VRAM
RTX 4070 Ti workstation
Best Local LLMs for RTX 4070 Ti in 2026: 12 GB VRAM Picks
12 GB VRAM local LLM picks for RTX 4070 Ti builds.
32 GB RAM12 GB VRAM
RTX 4070 workstation
Best Local LLMs for RTX 4070 in 2026: 12 GB VRAM Picks
12 GB VRAM local LLM picks for RTX 4070 and RTX 4070 Super systems.
32 GB RAM12 GB VRAM
RTX 4060 Ti 16GB workstation
Best Local LLMs for RTX 4060 Ti 16GB in 2026: 16 GB VRAM Picks
16 GB VRAM local LLM picks for RTX 4060 Ti 16GB systems.
32 GB RAM16 GB VRAM
RTX 4060 Ti 8GB workstation
Best Local LLMs for RTX 4060 Ti 8GB in 2026: 8 GB VRAM Picks
8 GB VRAM local LLM picks for RTX 4060 Ti 8GB systems.
32 GB RAM8 GB VRAM
RTX 4060 workstation
Best Local LLMs for RTX 4060 in 2026: 8 GB VRAM Picks
8 GB VRAM local LLM picks for RTX 4060 systems.
32 GB RAM8 GB VRAM
RTX 3090 workstation
Best Local LLMs for RTX 3090 in 2026: 24 GB VRAM Picks
24 GB VRAM local LLM picks for RTX 3090 workstations.
64 GB RAM24 GB VRAM
RTX 3080 workstation
Best Local LLMs for RTX 3080 in 2026: 10 GB VRAM Picks
10 GB VRAM local LLM picks for RTX 3080 systems.
32 GB RAM10 GB VRAM
RTX 3070 workstation
Best Local LLMs for RTX 3070 in 2026: 8 GB VRAM Picks
8 GB VRAM local LLM picks for RTX 3070 systems.
32 GB RAM8 GB VRAM
RTX 3060 Ti workstation
Best Local LLMs for RTX 3060 Ti in 2026: 8 GB VRAM Picks
8 GB VRAM local LLM picks for RTX 3060 Ti systems.
32 GB RAM8 GB VRAM
RTX 3060 workstation
Best Local LLMs for RTX 3060 in 2026: 12 GB VRAM Picks
12 GB VRAM local LLM picks for RTX 3060 systems.
32 GB RAM12 GB VRAM
Apple Silicon MacBook
Best Local LLMs for MacBook in 2026: Apple Silicon Picks
MacBook-friendly local LLMs for Apple Silicon unified memory.
16 GB RAMNo GPU
Last updated/Rankings by use case Jun 23, 2026/API prices Jun 23, 2026/Local LLM Jun 23, 2026
What changed
The homepage now works as a model-decision entry point, not a single tool page.
The core paths are AI Rankings, API Prices, Local Models, LLM Tests, and AI Radar. Each path links into methodology, official sources, real-world tests, or pricing data.
Review methodologyResearch paths
Compare AI models, AI API pricing, and local LLM hardware fit
Best AI model rankings
AI API pricing calculators
Local LLM hardware guides
Local AI Model FinderBest Local LLMs for 8GB RAM in 2026: Ollama, LM Studio, and Model PicksBest Local LLMs for 16GB RAM in 2026: Ollama and LM Studio PicksBest Local LLMs for 32GB RAM in 2026: 7B, 8B, and 14B PicksBest Local LLMs for RTX 5090 in 2026: 32 GB VRAM PicksBest Local LLMs for RTX 5080 in 2026: 16 GB VRAM PicksBest Local LLMs for RTX 5070 Ti in 2026: 16 GB VRAM PicksBest Local LLMs for RTX 5070 in 2026: 12 GB VRAM PicksBest Local LLMs for RTX 5060 Ti 16GB in 2026: 16 GB VRAM PicksBest Local LLMs for RTX 5060 Ti 8GB in 2026: 8 GB VRAM PicksBest Local LLMs for RTX 5060 in 2026: 8 GB VRAM PicksBest Local LLMs for RTX 4090 in 2026: 24GB VRAM PicksBest Local LLMs for RTX 4080 in 2026: 16 GB VRAM PicksBest Local LLMs for RTX 4070 Ti Super in 2026: 16 GB VRAM PicksBest Local LLMs for RTX 4070 Ti in 2026: 12 GB VRAM PicksBest Local LLMs for RTX 4070 in 2026: 12 GB VRAM PicksBest Local LLMs for RTX 4060 Ti 16GB in 2026: 16 GB VRAM PicksBest Local LLMs for RTX 4060 Ti 8GB in 2026: 8 GB VRAM PicksBest Local LLMs for RTX 4060 in 2026: 8 GB VRAM PicksBest Local LLMs for RTX 3090 in 2026: 24 GB VRAM PicksBest Local LLMs for RTX 3080 in 2026: 10 GB VRAM PicksBest Local LLMs for RTX 3070 in 2026: 8 GB VRAM PicksBest Local LLMs for RTX 3060 Ti in 2026: 8 GB VRAM PicksBest Local LLMs for RTX 3060 in 2026: 12 GB VRAM PicksBest Local LLMs for MacBook in 2026: Apple Silicon Picks
High-intent starting points
AI provider radar
FAQ
AI Jupyter FAQ
What is AI Jupyter?
AI Jupyter is a model-decision site for comparing AI rankings, official API prices, local LLM hardware fit, and official provider changes.
How is this different from a normal AI news site?
The homepage points to auditable rankings, pricing calculators, hands-on local tests, and official-source radar items instead of a generic news feed.
When should I use API Prices?
Use API Prices when you need production cost estimates that include retries, cache hits, batch jobs, long prompts, and output-token-heavy workloads.
When should I use Local Models?
Use Local Models when you want to run a model on your own machine, then narrow the choice by 8GB RAM, 16GB RAM, RTX 4090, MacBook, or real-world tests.