# AgentKernel

> Neutral comparison of AI models: prices, context windows, performance indices, head-to-head rankings for images, video and speech, privacy (zero data retention, EU hosting) and open vs proprietary licences, with no favoured provider. Data synced hourly; as of Oct 14, 2026, 15:00 UTC. English at https://www.agentkernel.si/, German at https://www.agentkernel.si/de/.

## Key facts
- Catalog: 360 language models and variants from 52 providers, plus 178 models for images, video, speech, transcription, music and embeddings.
- Rule of thumb for English text: 1 token ≈ 0.75 words. 1M tokens ≈ 750,000 words ≈ 3,000 pages ≈ 10 novels. For German text: 1 token ≈ 0.6 words.
- Privacy: 260 language models available with zero data retention, 57 of them in an EU region; 150 with open weights.
- Prices are base rates in US dollars per 1M input or output tokens, without caching, tiered pricing or taxes.

## Best model per task (one page each, updated hourly)
- [Overall](https://www.agentkernel.si/best-ai/overall/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/gesamt/)
- [Coding](https://www.agentkernel.si/best-ai/coding/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/coding/)
- [Agents](https://www.agentkernel.si/best-ai/agents/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/agenten/)
- [Websites](https://www.agentkernel.si/best-ai/websites/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/websites/)
- [UI components](https://www.agentkernel.si/best-ai/ui-components/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/ui-komponenten/)
- [Game development](https://www.agentkernel.si/best-ai/game-development/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/spieleentwicklung/)
- [Data visualisation](https://www.agentkernel.si/best-ai/data-visualization/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/datenvisualisierung/)
- [3D scenes](https://www.agentkernel.si/best-ai/3d-scenes/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/3d-szenen/)
- [SVG graphics](https://www.agentkernel.si/best-ai/svg-graphics/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/svg-grafiken/)
- [Web apps (agent)](https://www.agentkernel.si/best-ai/web-apps/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/web-apps/)
- [Full stack (agent)](https://www.agentkernel.si/best-ai/full-stack/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/full-stack/)
- [Mobile apps (agent)](https://www.agentkernel.si/best-ai/mobile-apps/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/mobile-apps/)
- [Create images](https://www.agentkernel.si/best-ai/image-generation/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/bilder-erstellen/)
- [Edit images](https://www.agentkernel.si/best-ai/image-editing/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/bilder-bearbeiten/)
- [Graphics & logos](https://www.agentkernel.si/best-ai/graphics-and-logos/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/grafik-und-logos/)
- [Video from text](https://www.agentkernel.si/best-ai/text-to-video/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/video-aus-text/)
- [Video from image](https://www.agentkernel.si/best-ai/image-to-video/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/video-aus-bild/)
- [Edit videos](https://www.agentkernel.si/best-ai/video-editing/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/video-bearbeiten/)
- [Text to speech](https://www.agentkernel.si/best-ai/text-to-speech/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/sprachausgabe/)
- [Transcription](https://www.agentkernel.si/best-ai/transcription/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/transkription/)
- [Music](https://www.agentkernel.si/best-ai/music/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/musik/)
- [Search & embeddings](https://www.agentkernel.si/best-ai/embeddings/) · [Deutsch](https://www.agentkernel.si/de/beste-ki/embeddings/)

## Model pages
- [All rated models](https://www.agentkernel.si/models/) · [Alle Modelle](https://www.agentkernel.si/de/modelle/): price, performance rank, context, privacy and cheaper alternatives per model.

## Use AgentKernel inside AI assistants (MCP)
- Remote MCP server (Streamable HTTP, read-only, no account): https://www.agentkernel.si/mcp · [Setup for Claude, ChatGPT, Cursor, VS Code](https://www.agentkernel.si/mcp-server/)
- Tools: best_for_task, recommend_models, get_model, find_models, estimate_cost, cheaper_alternative.
- Embeddable ranking badges: https://www.agentkernel.si/badge/<provider>/<model>.svg (optional ?task=<slug>&lang=de&theme=light).

## Interactive tools
- [Model finder](https://www.agentkernel.si/#finder): recommendations by use case, budget, priority, privacy and licence.
- [Cost calculator](https://www.agentkernel.si/#tokens): what a budget means in chat replies, emails, summaries, code reviews and book analyses.
- [Method](https://www.agentkernel.si/#methodik): Fit Score formula and data sources.

## Data
- [Catalog as a Markdown table (English)](https://www.agentkernel.si/models.md)
- [Katalog als Markdown-Tabelle (Deutsch)](https://www.agentkernel.si/modelle.md)
- [Catalog as JSON](https://www.agentkernel.si/api/models)

## Strongest model per provider (AgentKernel performance index)
- [Claude Opus 5.5](https://www.agentkernel.si/models/anthropic/claude-opus-5.5/) (Anthropic): 57.6 points, $4.00 input / $20.00 output per 1M tokens, 1000000 tokens context
- [GPT-6 Astra](https://www.agentkernel.si/models/openai/gpt-6-astra/) (OpenAI): 52.7 points, $10.00 input / $50.00 output per 1M tokens, 1050000 tokens context, coding index 76.9, agentic index 51
- [Gemini 4 Argon](https://www.agentkernel.si/models/google/gemini-4-argon/) (Google): 52.6 points, $2.00 input / $10.00 output per 1M tokens, 1048576 tokens context
- [Muse Spark 1.3](https://www.agentkernel.si/models/meta/muse-spark-1.3/) (Meta): 48.1 points, $1.25 input / $4.25 output per 1M tokens, 1048576 tokens context, coding index 75.8, agentic index 55.5
- [Grok 4.7](https://www.agentkernel.si/models/x-ai/grok-4.7/) (xAI): 46.4 points, $2.00 input / $6.00 output per 1M tokens, 500000 tokens context
- [MiMo-V2.6-Pro](https://www.agentkernel.si/models/xiaomi/mimo-v2.6-pro/) (Xiaomi): 46.3 points, $0.435 input / $0.87 output per 1M tokens, 1050000 tokens context
- [Qwen3.8 Max (0902)](https://www.agentkernel.si/models/qwen/qwen3.8-max-0902/) (Qwen): 45.4 points, $2.00 input / $6.00 output per 1M tokens, 1000000 tokens context, coding index 76.2, agentic index 56
- [GLM 5.3](https://www.agentkernel.si/models/z-ai/glm-5.3/) (Z.ai): 44.8 points, $0.079 input / $4.80 output per 1M tokens, 1048576 tokens context, coding index 74.8, agentic index 53.1

## Frequently asked questions
### What is a token?
A token is a small piece of text, usually part of a word. AI models read, write and bill in tokens. As a rule of thumb, one token is about 0.75 English words: 1,000 tokens are roughly 750 words or three pages.

### What can I do with one million tokens?
One million tokens are about 750,000 words, roughly 3,000 pages or 10 novels. That covers, for example, about 1,300 detailed chat replies, 1,500 email drafts or around 260 summaries of ten-page documents.

### How much does an AI model cost per month?
At 1M input and 250,000 output tokens per month, the 211 rated paid models in the AgentKernel catalog cost between $0.037 and $300.00, with a median of $0.90 (API base rates, as of Oct 14, 2026). Chat subscriptions are billed differently; free variants usually come with usage limits.

### Which AI model is the best?
It depends on the task and the budget. The strongest model from each of 5 providers is only 11.2 points apart on the AgentKernel performance index. The model finder weighs performance, cost, context and features for your use case instead of crowning a winner.

### Which AI model is best for coding?
118 models in the AgentKernel catalog have a coding index. The strongest coding model from each of 5 providers is 5.4 points apart, so price and context often decide more than rank. In the model finder, the Coding profile averages the general performance index with the coding index.

### Which AI model is best for creating images?
The AgentKernel catalog lists 57 image models. In head-to-head user votes, GPT Image 2.5 Sunburst (OpenAI), GPT Image 2.5 Flare (OpenAI), GPT Image 2 (medium) (OpenAI) currently lead. Which one fits depends on style, text in the image and price; the leaderboard also ranks image editing and graphics & logos separately.

### Which AI models can create videos?
30 video models are in the catalog, 17 of them with generated sound, clips up to 30 seconds and prices from $0.02 per second of video.  In head-to-head user votes for video from text, Gemini Omni 1.1 Flash (Google), Gemini Omni Flash (Google), FLUX 3 Video (Black Forest Labs) currently lead. The leaderboard ranks video from text, from an image and video editing separately and shows which of them you can book via API.

### Which AI voice (text to speech) sounds best?
In blind head-to-head votes, Inworld TTS MAX (Inworld), CastleFlow v1.0 (Async), Aurora (–) currently sound the most natural. The leaderboard shows the full ranking with vote counts and uncertainty, plus which models have open weights.

### Which AI models can I use without my data being stored, or in the EU?
260 language models in the catalog are offered by at least one provider with zero data retention, meaning prompts and responses are not stored; 57 of them also in an EU region. 150 models have open weights and can be self-hosted. The model finder can filter for both; this is provider information, not legal advice.

### What is a context window?
The context window is the largest amount of text a model can handle in a single request, measured in tokens: your question, attached documents, the conversation history and the answer together. 115 models in the catalog handle at least 1M tokens, roughly 3,000 pages at once.

### What is the difference between input and output tokens?
Input tokens are the text you send to the model, output tokens the text it writes. Output is usually much more expensive: in the AgentKernel catalog the median output price is 4 times the input price. Long documents with short answers are therefore often cheaper than you might expect.

### How current is the data?
The AgentKernel catalog of 360 models from 52 providers is synced every hour and the news every 15 minutes. This page reflects data as of Oct 14, 2026. Prices are the listed base rates in US dollars per million tokens.

### How is the AgentKernel Fit Score calculated?
The Fit Score combines four components from 0 to 100: overall performance, budget headroom, context headroom and matching features. The weighting depends on your use case and priority; the full formula is in the Method section.