# Fieldbook to AI

> The plain-English guide to which AI to use. Pick a task and see a best pick, a budget pick and a free option; see what everyday jobs cost; compare popular AIs like ChatGPT vs Claude. Costs are computed from OpenRouter's public list prices. These numbers are developer (API) prices, not the monthly plans for apps like ChatGPT, Claude or Gemini. For what the apps charge, see What should I pay? Verdicts are editorial, not our own tests. Last updated 2026-10-16.

## Start here
- [Which AI is best for writing?](https://fieldbooktoai.com/for/write)
- [Which AI is best for research?](https://fieldbooktoai.com/for/research)
- [Which AI is best for studying?](https://fieldbooktoai.com/for/study)
- [Which AI is best for coding?](https://fieldbooktoai.com/for/code)
- [Which AI is best for making pictures?](https://fieldbooktoai.com/for/images)
- [Which AI is best for work documents?](https://fieldbooktoai.com/for/work-docs)
- [Which AI is best for translation?](https://fieldbooktoai.com/for/translate)

## What should I pay? (app plans)
- [All plans: free vs about $20 vs $100 to $200](https://fieldbooktoai.com/plans)
- [ChatGPT plans and prices](https://fieldbooktoai.com/plans/chatgpt)
- [Claude plans and prices](https://fieldbooktoai.com/plans/claude)
- [Gemini plans and prices](https://fieldbooktoai.com/plans/gemini)
- [Grok plans and prices](https://fieldbooktoai.com/plans/grok)
- [Microsoft Copilot plans and prices](https://fieldbooktoai.com/plans/microsoft-copilot)
- [Meta AI plans and prices](https://fieldbooktoai.com/plans/meta-ai)
- [Perplexity plans and prices](https://fieldbooktoai.com/plans/perplexity)
- [plans.json](https://fieldbooktoai.com/data/plans.json), [plans.csv](https://fieldbooktoai.com/data/plans.csv)

## Comparisons
- [ChatGPT vs Claude](https://fieldbooktoai.com/compare/chatgpt-vs-claude)
- [Claude vs Gemini](https://fieldbooktoai.com/compare/claude-vs-gemini)
- [Cheap Claude vs cheap ChatGPT](https://fieldbooktoai.com/compare/cheap-claude-vs-cheap-chatgpt)

## Best-of guides
- [Best AI for writing](https://fieldbooktoai.com/best/writing): For everyday writing, Claude Sonnet 5.5 is our pick for the best balance of quality and price; Claude Haiku 5.5 is the cheap choice.
- [Best AI for coding](https://fieldbooktoai.com/best/coding): For programming help, Claude Opus 5.5 is our pick when quality matters most, and Claude Sonnet 5.5 is the better value.
- [Cheapest good AI models](https://fieldbooktoai.com/best/cheapest): For lots of everyday work at the lowest cost, Claude Haiku 5.5, GPT-6 Luna and DeepSeek V4.1 Flash are the main low-cost choices; Schematron is the cheapest for turning web pages into data.
- [Best AI for long documents](https://fieldbooktoai.com/best/long-documents): Most current top and fast models can read well over a thousand pages at once, so choose on price and quality: Claude Haiku 5.5 or DeepSeek V4.1 Flash for cheap passes, Claude Opus 5.5 for the hardest reading.
- [Best AI models you can download for free](https://fieldbooktoai.com/best/free-to-download): Xiaomi MiMo-V2.6-Pro is the smartest downloadable model we track; for running on your own computer, look at Qwen3.8 27B or Gemma 4 31B.
- [Best AI for pictures, audio and video](https://fieldbooktoai.com/best/images-and-video): Gemini 4 Argon can take in text, pictures, audio, video and files; Qwen3.8 Flash and Nemotron 3.5 Super VL are low-cost options for pictures and video.

## Time-savers
- [Clear your inbox in minutes](https://fieldbooktoai.com/time-savers/clear-your-inbox): Every new email gets sorted by urgency, and the ones that need a reply come with a draft waiting for you to review.
- [Turn meeting recordings into a to-do list](https://fieldbooktoai.com/time-savers/meeting-notes-to-tasks): After each meeting, you get the decisions, who owes what, and open questions, ready to paste into your task list or chat.
- [Turn web pages into a spreadsheet](https://fieldbooktoai.com/time-savers/web-pages-to-spreadsheet): Point it at product, job or listing pages and get tidy rows of data in a spreadsheet, at a tiny cost per page.
- [Get a weekly news digest on what you follow](https://fieldbooktoai.com/time-savers/weekly-news-digest): Every Monday you get a short email with the notable news on the companies or topics you pick, each with a link.
- [Get a first check on code changes (for developers)](https://fieldbooktoai.com/time-savers/check-code-before-a-human-does): Every time someone proposes a code change, a model reads it and leaves a short comment on likely problems before a person looks.

## Models
- [Claude Opus 5.5](https://fieldbooktoai.com/models/anthropic-claude-opus-5-5): The strongest all-round pick when quality matters more than cost, especially for big, complicated jobs like long coding projects. 1,000-word essay: $0.03 (about 3 cents).
- [Claude Sonnet 5.5](https://fieldbooktoai.com/models/anthropic-claude-sonnet-5-5): The sensible default: close to the top tier for writing, fixing code and everyday work, at about half the price of Claude Opus 5.5. 1,000-word essay: $0.01 (about 1 cent).
- [Claude Fable 5.1](https://fieldbooktoai.com/models/anthropic-claude-fable-5-1): A premium Claude model for long, multi-step jobs and knowledge work. It costs 2.5 times as much as Claude Opus 5.5. 1,000-word essay: $0.07 (about 7 cents).
- [GPT-6 Astra](https://fieldbooktoai.com/models/openai-gpt-6-astra): OpenAI's top model, built for deep research, programming and creating documents. Priced to match. 1,000-word essay: $0.07 (about 7 cents).
- [GPT-6.1 Sol](https://fieldbooktoai.com/models/openai-gpt-6-1-sol): Good value from OpenAI: strong at programming and working through long documents, at a mid-range price. 1,000-word essay: $0.01 (about 1 cent).
- [Gemini 4 Argon](https://fieldbooktoai.com/models/google-gemini-4-argon): Google's top model. It can read text, pictures, audio, video and files, at a mid-range price. 1,000-word essay: $0.01 (about 1 cent).
- [Muse Wonder](https://fieldbooktoai.com/models/meta-muse-wonder): Meta's top model for complex personal and work tasks. It understands text, pictures, video, audio and PDFs. 1,000-word essay: $0.03 (about 3 cents).
- [Grok 4.7](https://fieldbooktoai.com/models/x-ai-grok-4-7): Grok's top model, aimed at programming and long, multi-step jobs, priced below most top models. 1,000-word essay: $0.01 (about 1 cent).
- [Mistral Large 4](https://fieldbooktoai.com/models/mistralai-mistral-large-4-0): A low-cost large model from Mistral. A good choice when budget is tight but you still want a big model. 1,000-word essay: under 1 cent.
- [Command A+](https://fieldbooktoai.com/models/cohere-command-a-plus): Built for business use, where answers must follow a strict format. Priced low. 1,000-word essay: under 1 cent.
- [Claude Haiku 5.5](https://fieldbooktoai.com/models/anthropic-claude-haiku-5-5): The cheap and fast Claude. Great for summaries, quick questions and anything you do a lot of. 1,000-word essay: under 1 cent.
- [GPT-6 Luna](https://fieldbooktoai.com/models/openai-gpt-6-luna): OpenAI's fast, cheap model for chat, sorting things into groups and light tasks. 1,000-word essay: under 1 cent.
- [Gemini 3.8 Flash](https://fieldbooktoai.com/models/google-gemini-3-8-flash): Google's best fast model: a middle ground between cheap and capable. It understands audio and video too. 1,000-word essay: $0.01 (about 1 cent).
- [Muse Spark 1.3](https://fieldbooktoai.com/models/meta-muse-spark-1-3): A mid-priced Meta model for long, multi-step jobs and programming. It scores close to the top models. 1,000-word essay: $0.01 (about 1 cent).
- [DeepSeek V4.1 Flash](https://fieldbooktoai.com/models/deepseek-deepseek-v4-1-flash): Very low price, can be downloaded and run yourself, and reads a very large amount at once. Hard to beat for big batches of work. 1,000-word essay: under 1 cent.
- [Qwen3.8 Flash](https://fieldbooktoai.com/models/qwen-qwen3-8-flash): A cheap model that understands pictures and video, and can be downloaded and run yourself. 1,000-word essay: under 1 cent.
- [MiMo-V2.6-Flash](https://fieldbooktoai.com/models/xiaomi-mimo-v2-6-flash): One of the cheapest models we track. It understands audio and video too, and can be downloaded and run yourself. 1,000-word essay: under 1 cent.
- [Muse Spark Open](https://fieldbooktoai.com/models/meta-muse-spark-open): A downloadable Meta model tuned for programming. The one to watch if you want to run your own coding helper. 1,000-word essay: $0.01 (about 1 cent).
- [MiMo-V2.6-Pro](https://fieldbooktoai.com/models/xiaomi-mimo-v2-6-pro): The smartest downloadable model we track, at a very low price. 1,000-word essay: under 1 cent.
- [Kimi K3](https://fieldbooktoai.com/models/moonshotai-kimi-k3): A very large downloadable model for complicated programming and long jobs. 1,000-word essay: $0.02 (about 2 cents).
- [GLM 5.3](https://fieldbooktoai.com/models/z-ai-glm-5-3): A downloadable model for software work and long jobs, with very cheap input. 1,000-word essay: $0.01 (about 1 cent).
- [Qwen3.8 27B](https://fieldbooktoai.com/models/qwen-qwen3-8-27b): A mid-size downloadable model that understands pictures and video, and is realistic to run on your own hardware. 1,000-word essay: under 1 cent.
- [Nemotron 3.5 Super VL](https://fieldbooktoai.com/models/nvidia-nemotron-3-5-super-vl): A downloadable model that reads documents, screenshots and video at low cost. A free listing exists on OpenRouter. 1,000-word essay: under 1 cent.
- [gpt-oss-120b](https://fieldbooktoai.com/models/openai-gpt-oss-120b): OpenAI's older downloadable model. Still a cheap, well-known starting point for running your own. 1,000-word essay: under 1 cent.
- [Gemma 4 31B](https://fieldbooktoai.com/models/google-gemma-4-31b-it): Google's downloadable model, small enough to run yourself. It understands pictures and video. A free listing exists on OpenRouter. 1,000-word essay: under 1 cent.
- [DeepSeek V4 Pro 0813](https://fieldbooktoai.com/models/deepseek-deepseek-v4-pro-0813): DeepSeek's larger downloadable model at a low price. A cheap step up from DeepSeek V4.1 Flash. 1,000-word essay: under 1 cent.
- [LFM2.5-24B-A2B](https://fieldbooktoai.com/models/liquid-lfm-2-5-24b-a2b): A small downloadable model built to run on modest hardware. 1,000-word essay: under 1 cent.
- [Schematron V2 Turbo](https://fieldbooktoai.com/models/inference-net-schematron-v2-turbo): A tiny model that does one thing: turn a web page into a neat table of data, very cheaply. 1,000-word essay: under 1 cent.
- [Moondream 3.1](https://fieldbooktoai.com/models/moondream-moondream3-1-9b-a2b): A small model for answering questions about images, describing them and reading text in them. 1,000-word essay: under 1 cent.
- [Nano Banana 2.1](https://fieldbooktoai.com/models/google-gemini-nano-banana-2-1): Google's model for creating and editing images, for product shots and photo edits. 1,000-word essay: $0.01 (about 1 cent).
- [Hy-MT2-7B](https://fieldbooktoai.com/models/tencent-hy-mt2-7b): A model built only for translation, with options for glossaries and writing style. Covers 33 language pairs plus some Chinese dialects. 1,000-word essay: under 1 cent.
- [Sonar Pro](https://fieldbooktoai.com/models/perplexity-sonar-pro): Answers questions by searching the web and showing its sources. A research helper rather than a general chatbot. 1,000-word essay: $0.02 (about 2 cents).

## Data
- [Models CSV](https://fieldbooktoai.com/data/models.csv)
- [Models JSON](https://fieldbooktoai.com/data/models.json)
- [Advanced table](https://fieldbooktoai.com/advanced)
- [How we work](https://fieldbooktoai.com/about)
- [Changelog](https://fieldbooktoai.com/changelog)