---
title: "Models"
description: "The AI models in the vetted library, with each fact linked to the page it came from."
canonical: "https://vetted.tools/models"
source: "https://vetted.tools/models.md"
---

# Models

The AI models in the vetted library, with each fact linked to the page it came from.

Source: https://vetted.tools/models

The AI models behind chat apps and assistants: what each one costs, how much it can read at once, and whether the Vercel AI Gateway can keep your prompts from being stored or trained on.

26 models. Newest release first.

| Model | What it does |
| --- | --- |
| [Claude Opus 5.5](https://vetted.tools/models/claude-opus-5-5) | Anthropic's model for long-running agentic coding and knowledge work, 1M-token context. |
| [GPT-6 Luna](https://vetted.tools/models/gpt-6-luna) | OpenAI's most efficient GPT-6 model, for focused, high-volume tasks. |
| [GPT-6 Sol](https://vetted.tools/models/gpt-6-sol) | OpenAI model for complex coding and agentic workflows, with a 1.05M-token context. |
| [Grok 4.7](https://vetted.tools/models/grok-4-7) | xAI's flagship Grok model for code and agentic tool calling, with 500K-token context. |
| [MiMo V2.6 Pro](https://vetted.tools/models/mimo-v2-6-pro) | Xiaomi's flagship MiMo model: text, image, video and audio in, 1M-token context. |
| [Jev](https://vetted.tools/models/jev) | TypeSafe's decision model: it returns fast, structured decisions that software can use directly, instead of writing text. In early access through an API. |
| [DeepSeek V4.1 Flash](https://vetted.tools/models/deepseek-v4-1-flash) | DeepSeek's open-weights multimodal MoE model with a 1M-token context window. |
| [GPT-6 Astra](https://vetted.tools/models/gpt-6-astra) | OpenAI's most capable model, for the hardest work |
| [Gemini 3.8 Flash](https://vetted.tools/models/gemini-3-8-flash) | Google's Flash model for coding and agents, with reasoning at Flash-level latency. |
| [Claude Fable 5.1](https://vetted.tools/models/claude-fable-5-1) | Anthropic's model for demanding reasoning and long-horizon agentic work. |
| [Hunyuan Hy4 (preview)](https://vetted.tools/models/hunyuan-hy4-preview) | Tencent's next open model, in preview |
| [GLM-5.3](https://vetted.tools/models/glm-5-3) | Z.ai's open-weights model, post-trained for complex coding and long-horizon tasks. |
| [Qwen3.8 27B](https://vetted.tools/models/qwen3-8-27b) | Qwen's compact 27B dense open model that reads text, images and video. |
| [Qwen 3.8 Max](https://vetted.tools/models/qwen3-8-max) | Qwen's largest model, for coding and professional work |
| [Kimi K3](https://vetted.tools/models/kimi-k3) | Moonshot's open-weights multimodal agent model: 2.8T parameters, 1M-token context. |
| [Hunyuan Hy3](https://vetted.tools/models/hunyuan-hy3) | Tencent's open-weights 295B MoE model with 21B active parameters, tuned for agents. |
| [Claude Sonnet 5](https://vetted.tools/models/claude-sonnet-5) | Anthropic's balance of speed and intelligence, with a 1M-token context window. |
| [Nemotron 3 Ultra](https://vetted.tools/models/nemotron-3-ultra) | NVIDIA's largest open Nemotron 3 model, 550B parameters, for agentic reasoning. |
| [MiniMax M3](https://vetted.tools/models/minimax-m3) | MiniMax's native multimodal model for coding and agents, with a 1M-token context. |
| [Nano Banana 2](https://vetted.tools/models/nano-banana-2) | Google's image generation and editing model, built on Gemini 3.1 Flash Image. Used in the Gemini app and through the Gemini API. |
| [DeepSeek V4 Pro](https://vetted.tools/models/deepseek-v4-pro) | DeepSeek's 1.6T-parameter open-weights MoE model with a 1M-token context window. |
| [Gemma 4 31B](https://vetted.tools/models/gemma-4-31b) | Google's open-weights 31B Gemma 4 model: text and image in, up to 256K context. |
| [Gemini 3.1 Pro (preview)](https://vetted.tools/models/gemini-3-1-pro-preview) | Google's Gemini Pro model for complex tasks, in preview. |
| [Mistral Large 3](https://vetted.tools/models/mistral-large-3) | Mistral's open-weight multimodal flagship |
| [Sonar Pro](https://vetted.tools/models/sonar-pro) | Perplexity's search model for complex questions, returning twice Sonar's results. |
| [Muse Spark 1.3](https://vetted.tools/models/muse-spark-1-3) | Meta's Muse Spark 1.3, with max reasoning for challenging reasoning and agentic tasks |

## Elsewhere on this site

- Home: https://vetted.tools/index.md
- Use cases: https://vetted.tools/use-cases.md
- Tools: https://vetted.tools/tools.md
- The brief: https://vetted.tools/brief.md
- Assessment: https://vetted.tools/assessment.md
- Site summary for agents: https://vetted.tools/llms.txt
- Every published page in one file: https://vetted.tools/llms-full.txt
- Every URL the site publishes: https://vetted.tools/sitemap.xml