AI model selection database · Updated May 2026
AI models, API prices & how to choose
Pick between GPT-5, Claude Sonnet 4.6, Gemini 2.5 Pro, Grok 4, DeepSeek R1, Qwen3 and Mistral with the actual numbers — not vibes. Below is a scenario-based picker; the live comparison tool is one click away.
Latest models
- Kat Coder Air V2.5 released 2026-07-10
- Kat Coder Pro V2.5 released 2026-07-10
- GPT-5.6 Luna released 2026-07-09
- GPT-Realtime-2.1 released 2026-07-09
- GPT-5.6 Terra released 2026-07-09
- GPT-5.6 Sol released 2026-07-09
- Muse Spark 1.1 released 2026-07-09
- GPT-5.6 Terra Pro released 2026-07-09
Pick by scenario
Head-to-head comparisons
Every major model pair has its own page with the same numbers the live tool serves: pricing, context, SWE-bench, LMArena, capability matrix.
- GPT-5 vs Claude Sonnet 4.6
- Claude Sonnet 4.6 vs DeepSeek R1
- Gemini 2.5 Pro vs GPT-5
- DeepSeek R1 vs GPT-5
- The 2026 Chinese AI Model Landscape: How to Choose Among DeepSeek, Qwen, Kimi, GLM, MiniMax
- Claude Opus 4.7 Review: SWE-bench 87.6%, Same Price, Who Should Upgrade
- DeepSeek R1 vs GPT-5: How Many Times Cheaper, Really
- GPT-5 vs Claude Sonnet 4.6: Which to Pick for Coding
- The Complete Guide to Running Open-Source LLMs Locally: GPU, VRAM, Frameworks, Models
- RAG vs Long Context vs Fine-tune 2026: A Complete Guide to What to Pick When
- ChatGPT vs Claude vs Gemini: Which Subscription to Buy (2026)
- Which Model to Use for AI Agents in 2026: Tool Calling, Long Tasks, Real Costs
- Claude Opus 4.8 Is Out: Still $5/$25, 1M Context, Should You Upgrade from 4.7
- Claude Fable 5 Is Out: Price Doubles to $10/$50, How It Differs from Mythos 5, Who Should Upgrade
About the data
Prices, context windows and capabilities come from provider docs and the open-source models.dev dataset, checked weekly. Benchmark scores: LMArena, SWE-bench, HumanEval, MMLU, plus provider-published evals. Editorial calls: the Check.AI maintainer.