Tokens
The small pieces of text a model reads and writes, roughly three-quarters of an English word each. API prices are quoted per million tokens.
Where every number on AI Toolbelt comes from, what it means, and what it leaves out.
A free public guide to choosing an AI app or API model. Prices, limits, and scores are spread across dozens of vendor pages and change often; this guide puts them in one place. Labs cannot pay for placement. The site has no affiliate links, sets no cookies, and runs no analytics.
Standard, uncached API rates in US dollars per million tokens, taken directly from each lab’s pricing or model page. Announced price changes are stored with their effective start date, and the site switches automatically on that day. Unknown prices are shown as “Not published”, never as zero.
The Intelligence Index is Artificial Analysis’s combined score across its independent benchmark suite. Points are not percentages. Each model’s headline score is from Artificial Analysis’s default run, usually its highest reasoning effort; the map, table, and compare page can switch to any other tested effort level.
Reasoning effort never changes the price per token at any of the five labs. It changes how many tokens a model spends: every lab bills thinking tokens as output. For flagship models, cost per task usually rises 5× to 10× from the lowest effort setting to the highest.
Effort can matter as much as model choice. GPT-6.2 Astra and Claude Fable 5.2 share an $8 / $40 list price, but at Max effort Astra spent $4.00 per benchmark task for 62.1 points while Fable spent $26.54 for 64.6.
Faster processing is the one setting that changes the per-token price: OpenAI Fast is 2× and Ultrafast is 3× on GPT-6.2 until 28 February 2027 (then 6×); Anthropic fast mode is 2×; Google and xAI Priority are 1.8× and 2×. The calculator applies them to every token rate and never combines them with batch discounts.
The consumer picker matches each everyday job to the features it requires: looking things up needs web search, learning and work documents need file uploads, and making images needs image generation. For your budget it shows the richest plan each app offers at or under that price, ordered cheapest first rather than ranked by opinion.
On app pages, models receive a plain rating from the Intelligence Index: Top tier (60+), Strong (50+), Capable (40+), and Basic below 40. Recommended effort on model pages is the cheapest setting within 2 points of the model’s best score.
Your compare list and theme preference stay in your browser’s local storage. Data is CC BY 4.0 and code is MIT licensed. Product names and logos (Lobe Icons, MIT) are trademarks of their owners used for identification.
Every technical term used across our maps, tables, and cost calculator, defined without jargon.
The small pieces of text a model reads and writes, roughly three-quarters of an English word each. API prices are quoted per million tokens.
How much text a model can hold at once, counting both what you send and what it writes back.
A setting for how long a model thinks before it answers. It never changes the price per token; higher settings spend more thinking tokens and time, so each task costs more.
Artificial Analysis’s combined score across a suite of independent tests. Points are not percentages.
Sending requests to be processed later, usually within a day, at a lower price where the lab offers one.
Prompt text the lab has already processed and stored, such as a long system prompt. It is billed at a lower rate when reused.
The working-out a model writes before its answer, also called reasoning tokens. Every lab here bills them as output tokens, even when you never see them.
Paying more per token for faster or first-in-line processing: Fast and Ultrafast at OpenAI, fast mode at Anthropic, Priority at Google and xAI. Unlike effort, it changes the price.
Every vendor page and independent benchmark checked on 21 Nov 2026.
| Source | Notes | Link |
|---|---|---|
| OpenAI · Terra specifications | Official documentation | Open |
| OpenAI · Sol specifications | Official documentation | Open |
| OpenAI · Astra specifications | Official documentation | Open |
| OpenAI · Luna specifications | Official documentation | Open |
| OpenAI · API pricing (Ultrafast, background) | Official pricing | Open |
| Anthropic · API pricing | Official pricing | Open |
| Anthropic · models overview | Official documentation | Open |
| Anthropic · Claude plans | Official pricing | Open |
| Anthropic · Haiku 5.5 announcement | Vendor announcement | Open |
| Google · Gemini API pricing | Official pricing | Open |
| Google · Neon model card | Official model card | Open |
| Google · Hydrogen model card | Official model card | Open |
| Google · Introducing Gemini 4 Neon | Vendor announcement | Open |
| Google · Gemini 4 Argon launch (1M output) | Vendor announcement | Open |
| Google · Carbon model card | Official model card | Open |
| Microsoft · Ignite model lineup | Vendor announcement | Open |
| Microsoft · Code 2 evaluation footnotes | Vendor evaluation | Open |
| Microsoft · MAI Thinking 1 | Vendor announcement | Open |
| Artificial Analysis · model leaderboard | Independent measurement | Open |
| Artificial Analysis · Google endpoints | Independent measurement | Open |
| xAI · Grok 4.7 model page | Official documentation | Open |
| Artificial Analysis · Grok 4.7 | Independent benchmark | Open |
| Google · Gemini 4 Carbon model page (token limits) | Official documentation | Open |
| Microsoft Azure · Foundry Models pricing | Official pricing | Open |
| GitHub Docs · Models and pricing for GitHub Copilot | Official documentation | Open |
| OpenAI · GPT-6 Astra specifications | Official documentation | Open |
| OpenAI · GPT-6.1 Sol specifications | Official documentation | Open |
| Google · Gemini 3.8 Flash model page | Official documentation | Open |
| Artificial Analysis · GPT-6 Astra | Independent measurement | Open |
| Artificial Analysis · GPT-6.1 Sol | Independent measurement | Open |
| Artificial Analysis · Gemini 3.8 Flash | Independent measurement | Open |
| OpenAI · ChatGPT Work & Codex pricing | Official pricing, surfaces, models and per-plan limits for Codex | Open |
| OpenAI · ChatGPT plans and pricing | Official pricing; shows local currency by region (read from Canada, CA$), used here for plan contents, models and feature table only | Open |
| OpenAI · Introducing GPT-6.2 Astra and Sol | Vendor announcement, 17 Nov 2026 | Open |
| OpenAI Help · About ChatGPT Pro tiers | Official help | Open |
| OpenAI Help · What is ChatGPT Go? | Official help; no annual billing for Go, Plus or Pro | Open |
| Google · Gemini subscriptions (US) | Official pricing; Antigravity rate limits per Google AI plan | Open |
| SpaceXSI (xAI) · Pricing | Official pricing; same plans as cursor.com/pricing | Open |
| SpaceXSI (xAI) · Grok product page | Official product page; feature list | Open |
| SpaceXSI Docs · What is The X Subscription? | Official docs (updated 2026-10-12); one plan for Grok, X and Cursor, shared weekly pool, switching is optional | Open |
| SpaceXSI Docs · X Premium customers moving to The X Subscription | Official docs (updated 2026-11-03); X benefits by plan | Open |
| X Help Center · About X Premium | Official help; X Premium is now part of The X Subscription; legacy US prices Basic $3, Premium $8, Premium+ $40 a month | Open |
| Microsoft · Copilot plans for individuals | Official pricing; monthly prices (a 30% first-period promotion was running on 2026-11-20) | Open |
| Microsoft · Microsoft 365 for individuals (compare plans) | Official pricing; yearly prices and Copilot feature table | Open |
| Microsoft · Copilot home | Official; 'Microsoft Copilot is free with a signed-in Microsoft account' | Open |
| NBER w34255 · How People Use ChatGPT (2025) | Primary research (OpenAI economists); topic shares read from the full paper, section 4 | Open |
| OpenAI · How people are using ChatGPT | Vendor summary of the NBER paper | Open |
| Anthropic Economic Index · March 2026 report (Learning curves) | Primary research; Feb 5-12, 2026 sample | Open |
| Anthropic Economic Index · September 2025 report | Primary research (Claude.ai and API usage) | Open |
| Pew Research Center · 34% of U.S. adults have used ChatGPT (2025-06-25) | Survey of 5,123 U.S. adults, Feb 24 - Mar 2, 2025 | Open |
| Reuters Institute · Generative AI and News Report 2025 | Survey in 6 countries, fieldwork Jun 5 - Jul 15, 2025 | Open |
| Anthropic · Claude Code product page | Official; surfaces and which plans include it | Open |
| Anthropic · Claude Code overview docs | Official documentation; surfaces | Open |
| Google · Gemini CLI README | Official repository; status after the move to Antigravity CLI | Open |
| Google · Gemini CLI quotas and pricing | Official docs (last updated Jun 18, 2026) | Open |
| GitHub · Copilot plans | Official pricing | Open |
| GitHub Docs · Plans for GitHub Copilot | Official documentation | Open |
| Cursor · Pricing | Official pricing (shared plans with Grok / X) | Open |
| SpaceXSI (xAI) · Grok Build | Official product page | Open |