AI Model Cheat Sheet
Every major model's price, context window, and sweet spot — on one page you can bookmark. Last verified October 2026 · printable (Ctrl+P) · updated monthly alongside our price tracker.
⇅ Click a price or size column header to sort (click again to reverse).
| Model | Provider | Input $/1M | Output $/1M | Context | Max output | Best for |
|---|---|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1M | 64K | Bulk classification, tagging, cheapest possible calls | |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | 1M* | 128K* | New cheapest OpenAI model, half of GPT-5.6 Luna's price |
| Claude Haiku 5.5 | Anthropic | $0.10¤ | $0.50¤ | 1M | 128K | New cheapest Claude model, ~75% under Haiku 4.5; Haiku 4.5 remains available |
| GPT-5.6 Luna | OpenAI | $0.20 | $1.20 | 400K* | 128K* | Still available; superseded on price by GPT-6 Luna |
| GPT-5.4 Nano | OpenAI | $0.20 | $1.25 | 400K* | 128K* | High-volume simple tasks in the OpenAI stack |
| Gemini 2.5 Flash | $0.30 | $2.50 | 1M | 64K | Budget chat & summarization with big context | |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | 200K | 64K | Fast production workloads needing Claude quality |
| Gemini 3.6 Flash | $1.50¶ | $7.50¶ | 1M | 64K | Cheaper, more token-efficient successor to 3.5 Flash | |
| Gemini 3.7 Flash | $1.50† | $7.50† | 1M | 64K | Stronger coding & agent scores than 3.6 Flash at the same list price | |
| Gemini 3.8 Flash | $1.50§ | $7.50§ | 1M | 64K | Google's newest Flash, tuned for long-horizon coding & agents | |
| Gemini 3.5 Flash | $1.50 | $9.00 | 1M | 65K | Speed/intelligence balance, agentic browsing | |
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | 1M | 128K | Coding & agents near-frontier quality at flagship price |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | 1M | 128K | Same price as Sonnet 5, ~30% faster responses; Sonnet 5 remains available |
| GPT-6 Sol | OpenAI | $2.00 | $10.00 | 1M* | 128K* | OpenAI's new mid-tier default, half of GPT-5.6 Sol's intro rate |
| Gemini 3.1 Pro | $2.00 | $12.00 | 500K | 64K | Strong reasoning at mid-tier price | |
| GPT-5.6 Terra | OpenAI | $2.00 | $12.00 | 400K* | 128K* | Newest mainstream flagship, now priced with the mid tier |
| GPT-5.4 | OpenAI | $2.50 | $15.00 | 400K* | 128K* | Mainstream OpenAI production default |
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | 1M | 128K | Anthropic's new default frontier pick for long-horizon agentic coding, 20% under Opus 5 |
| Claude Opus 4.8 | Anthropic | $5.00 | $25.00 | 1M | 128K | Long-horizon agents, hard coding, knowledge work |
| Claude Opus 5 | Anthropic | $5.00 | $25.00 | 1M | 128K | Same price as Opus 4.8; superseded on price by Opus 5.5 |
| GPT-5.5 | OpenAI | $5.00 | $30.00 | 400K* | 128K* | OpenAI's frontier reasoning |
| GPT-5.6 Sol | OpenAI | $5.00‡ | $30.00‡ | 400K* | 128K* | Top of the GPT-5.6 family |
| Claude Fable 5 | Anthropic | $10.00 | $50.00 | 1M | 128K | The hardest reasoning and longest autonomous runs |
| Claude Fable 5.1 | Anthropic | $10.00 | $50.00 | 1M | 128K | Same as Fable 5, but cached input is 75% cheaper — best pick for heavy agentic/caching workloads |
| Claude Mythos 5.1 | Anthropic | $10.00‖ | $50.00‖ | 1M | 128K | Same weights & price as Fable 5.1, restricted to vetted cyberdefense/biosecurity orgs |
| GPT-6 Astra | OpenAI | $10.00 | $50.00 | 1M* | 128K* | OpenAI's new flagship for long-horizon agentic work & computer use |
Standard-tier list prices, October 2026. ¶Gemini 3.6 Flash has the same intro rate as 3.7 and 3.8 Flash, $0.75/$3.75 through Dec 31, 2026. †Gemini 3.7 Flash intro rate $0.75/$3.75 through Dec 31, 2026. §Gemini 3.8 Flash has the same intro rate, $0.75/$3.75 through Dec 31, 2026. ‡GPT-5.6 Sol intro rate $4.00/$20.00 through at least Nov 21, 2026. ‖Claude Mythos 5.1 is not generally available — Anthropic restricts it to organisations vetted under its Cyber and Life Sciences Verification Programs. ¤Claude Haiku 5.5's rate applies to prompts up to 100K tokens; above that, input/output rise to $0.50/$2.50. *GPT-5.x and GPT-6 family figures per OpenAI's published specs — confirm on OpenAI's model page for the exact variant. All listed models support vision input, prompt caching (~90% off repeated input, except Claude Fable 5.1 and Claude Mythos 5.1 at ~97.5% off and Claude Opus 5.5 at ~95% off), and batch (~50% off).
Quick picks — skip the analysis
Reading the spec sheet
- Context window = the model's working memory per request (your prompt + documents + history + its answer). 200K ≈ a 300-page book; 1M ≈ five of them.
- Max output = the longest single response. You pay output rates for it, so long outputs dominate cost in drafting/codegen workloads.
- Filling the whole context costs real money: 1M input tokens on a $3/1M model = $3 per request — caching is what makes big-context workflows affordable.
- Prices move ~monthly. This page and the price tracker are verified together — the date at the top is your freshness guarantee.
Anything on this page can be wrong within a week
Model pricing is not a stable specification. Providers cut prices, launch cheaper variants, deprecate older models and occasionally raise rates, and none of it comes with notice. A cheat sheet is therefore only as trustworthy as the date on it — which is why every figure here is generated from a single source file rather than typed into the page, and why a build check fails the deploy if any two pages on this site quote the same model differently.
What that does and does not buy you:
- It guarantees internal consistency. No page here can disagree with another about a price, because they all read the same table.
- It does not guarantee currency. If a provider changed a price this morning, this page is wrong until the table is updated. The review date at the foot of the page is the honest measure of how stale it might be.
- Before committing to a contract or a budget, check the provider's own pricing page. That is the only authoritative source, and it is the one every summary — including this one — is copied from.
Use a cheat sheet for what it is good at: narrowing a field of a dozen models to two or three worth pricing properly. Do the final arithmetic against the provider's numbers on the day you need them.
Frequently asked questions
Which single model should I default to?
For most production work in mid-2026: a flagship-tier model (Claude Sonnet 5, GPT-5.6 Terra, or Gemini 3.1 Pro) as the default, a budget model for easy traffic, and a frontier model only where quality visibly pays for itself.
Are benchmark scores on this page?
Deliberately not — leaderboard positions shuffle monthly and rarely predict your task. Price, context, and output limits are the stable facts; test your top 2–3 candidates on your own data.
How do I estimate my cost with these numbers?
Tokens ÷ 1,000,000 × price. Or skip the arithmetic: the AI cost calculator and token calculator do it live.
Can I print or save this?
Yes — Ctrl+P gives a clean printable version (navigation is stripped automatically). Bookmark the page for the monthly-updated version.
The guide that goes deeper
You might also need
🤖AI API Cost Calculator
Compare GPT, Claude & Gemini pricing and estimate monthly costs.
💠AI Pricing by Provider
Every model priced, compared within each provider lineup.
🔢Token Calculator
Token count and cost of any text, on every model.
💬Chatbot Cost Simulator
Monthly LLM bill for your product: users × messages × tokens.