# AgentKernel

> Neutral comparison of AI language models: prices, context windows, a performance index and a transparent Fit Score per use case, with no favoured provider. English at https://www.agentkernel.si/, German at https://www.agentkernel.si/de/. Data as of Oct 04, 2026.

## Key facts
- Catalog: 369 models and variants from 56 providers, synced hourly.
- 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.
- Prices are base rates in US dollars per 1M input or output tokens, without caching, tiered pricing or taxes.

## Pages
- [Model finder](https://www.agentkernel.si/#finder): recommendations by use case (everyday, coding, agents, documents), budget and priority.
- [Cost calculator](https://www.agentkernel.si/#tokens): what a budget means in chat replies, emails, summaries, code reviews and book analyses.
- [Catalog](https://www.agentkernel.si/#modelle): every model with prices, context and capabilities.
- [FAQ](https://www.agentkernel.si/#faq): tokens, costs and context explained.
- [Method](https://www.agentkernel.si/#methodik): full Fit Score formula and data sources.
- [German version](https://www.agentkernel.si/de/)

## 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 (Anthropic): 57.6 points, $4.00 input / $20.00 output per 1M tokens, 1000000 tokens context
- GPT-6 Astra (OpenAI): 52.7 points, $10.00 input / $50.00 output per 1M tokens, 1050000 tokens context
- Grok 4.7 (xAI): 46.4 points, $2.00 input / $6.00 output per 1M tokens, 500000 tokens context
- MiMo-V2.6-Pro (Xiaomi): 46.3 points, $0.435 input / $0.87 output per 1M tokens, 1050000 tokens context
- Qwen3.8 Max (0902) (Qwen): 45.4 points, $2.00 input / $6.00 output per 1M tokens, 1000000 tokens context
- GLM 5.3 (Z.ai): 44.8 points, $1.40 input / $4.40 output per 1M tokens, 1048576 tokens context
- Kimi K3 (Moonshot AI): 43.6 points, $0.72 input / $13.00 output per 1M tokens, 1048576 tokens context
- Gemini 3.8 Flash (Google): 40.9 points, $0.75 input / $3.75 output per 1M tokens, 1048576 tokens context

## 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 99 rated paid models in the AgentKernel catalog cost between $0.036 and $22.50, with a median of $0.90 (API base rates, as of Oct 04, 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 12.2 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.

### 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. 111 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 369 models from 56 providers is synced every hour and the news every 15 minutes. This page reflects data as of Oct 04, 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.