Whether you've never written code or ship to production daily: AgentCost tells you which AI model or agent fits your idea, what it really costs, and what other builders are using right now.
Top models by Coding Index
Scores: Artificial Analysis · Prices per 1M tokens (in / out)
Prices tracked from the official pages of
Start here
Tell us what you want to build, how much you code and your budget. You'll get a step-by-step plan with the exact tools and the model to use.
Step 1 of 3
AI 101
No jargon. Read this once and every page on AgentCost will make sense.
The “brain”. You send it text (or images, audio) and it sends back an answer. GPT, Claude, Gemini and DeepSeek are model families.
“Summarize this email” → a summary.
A model plus tools and a loop: it plans, takes actions (edit files, browse, call APIs), checks results and keeps going until the task is done.
“Add a login page” → it writes code, runs it, fixes errors.
How your app talks to a model. You pay per use instead of a monthly seat, which is why your volume decides the bill.
Your support page sends each question to the model's API.
The unit models are billed in — roughly ¾ of a word. Prices are “per 1M tokens”, with input (what you send) and output (what it writes) priced separately.
A 750-word article ≈ 1,000 tokens.
How much the model can read at once — its short-term memory. Bigger windows fit whole codebases or long documents in one request.
1M tokens ≈ several novels at once.
A standardized test that scores models on the same tasks, so you can compare quality fairly instead of trusting marketing.
Coding Index: how well a model solves real coding tasks.
You want an answer, text or a classification
→ A model
Call its API, or chat with it
You want a task done end-to-end
→ An agent
Use a ready agent or build one with a framework
You don't code and want a working app
→ An app-builder agent
Describe it, iterate by chatting
You want to cut cost
→ A smaller model
Use the “Best value” sort and test on real data
Compare AI models
Pick a use case, set your volume, and compare quality against what you'll actually pay.
Build software
Create media
Run in production
Backend development: APIs, services, databases, debugging and refactors across large codebases.
Every token-priced card shows its cost for this workload.
Based on Artificial Analysis scores and your workload estimate
Top performer
Highest Coding score among the models in view.
Best value
Most Coding per dollar — about 13× cheaper than the top performer.
Budget pick
Cheapest model that still scores above the median on Coding.
65 models · sorted by best fit
Coding
81.6
top 1%
Intelligence
53.4
top 1%
Agentic
57.9
top 1%
Input
$10
Cached input
$0.25
Output
$50
per 1M tokens · Standard
80× the cheapest in view
Coding
78
top 2%
Intelligence
50.8
top 3%
Agentic
56.5
top 2%
Input
$5
Cached input
$0.50
Output
$25
per 1M tokens · Standard
40× the cheapest in view
Coding
78.3
top 3%
Intelligence
47
top 5%
Agentic
50.2
top 13%
Input
$4
Cached input
$0.40
Output
$20
per 1M tokens · Standard
32× the cheapest in view
Coding
77.1
top 5%
Intelligence
52.7
top 2%
Agentic
51
top 9%
Input
$10
Cached input
$1
Output
$50
per 1M tokens · Standard
81× the cheapest in view
Coding
76.8
top 6%
Intelligence
44.3
top 7%
Agentic
53
top 6%
Input
$2
Cached input
$0.50
Output
$6
per 1M tokens · Standard · < 200k prompt tokens
13× the cheapest in view
Coding
76.7
top 7%
Intelligence
42.1
top 9%
Agentic
43.2
top 23%
Input
$2
Cached input
$0.20
Output
$12
per 1M tokens · Standard
18× the cheapest in view
Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.
Coding
76.3
top 9%
Intelligence
40.9
top 10%
Agentic
40.2
top 28%
Input
$0.75
Cached input
$0.075
Output
$3.75
per 1M tokens · Standard
6.1× the cheapest in view
Coding
74.9
top 13%
Intelligence
38.4
top 13%
Agentic
36.4
top 34%
Input
$5
Cached input
$0.50
Output
$30
per 1M tokens · Standard · <272K context length
45× the cheapest in view
Coding
74.3
top 15%
Intelligence
41.8
top 10%
Agentic
41.9
top 24%
Input
$5
Cached input
$0.50
Output
$25
per 1M tokens · Standard
40× the cheapest in view
Coding
73.6
top 16%
Intelligence
40.7
top 11%
Agentic
38.6
top 32%
Input
$5
Cached input
$0.50
Output
$25
per 1M tokens · Standard
40× the cheapest in view
Coding
72.4
top 17%
Intelligence
38.8
top 13%
Agentic
41.2
top 26%
Input
$2
Cached input
$0.30
Output
$6
per 1M tokens · Standard · < 200k prompt tokens
13× the cheapest in view
Coding
71.5
top 21%
Intelligence
38.2
top 13%
Agentic
43.6
top 21%
Input
$2
Cached input
$0.20
Output
$10
per 1M tokens · Standard
16× the cheapest in view
Coding
71.1
top 22%
Intelligence
39
top 12%
Web design
1218 Elo
#66 of 172
Input
$2.50
Cached input
$0.25
Output
$15
per 1M tokens · Standard · <272K context length
23× the cheapest in view
Coding
76.5
Intelligence
49.6
Agentic
50.7
Input
$10
Cached input
$1
Output
$50
per 1M tokens · Standard
81× the cheapest in view
Our previous generation Flash model, balancing speed and multimodal capabilities across general agentic and everyday tasks.
Coding
69.2
top 25%
Intelligence
34
top 17%
Agentic
29
top 42%
Input
$0.75
Cached input
$0.075
Output
$3.75
per 1M tokens · Standard
6.1× the cheapest in view
Our 3rd generation Pro model, built for multimodal understanding, agentic capabilities, and vibe-coding.
Coding
68.8
top 27%
Intelligence
29.7
top 21%
Agentic
8.2
top 70%
Input
$2
Cached input
$0.20
Output
$12
per 1M tokens · Standard
18× the cheapest in view
Coding
63
Intelligence
30.1
Agentic
31.8
Input
$3
Cached input
$0.30
Output
$15
per 1M tokens · Standard
24× the cheapest in view
Coding
52.1
top 47%
Intelligence
20.7
top 38%
Agentic
15.8
top 62%
Input
$3
Cached input
$0.30
Output
$15
per 1M tokens · Standard
24× the cheapest in view
Coding
51.5
Intelligence
27.2
Input
$1
Cached input
$0.20
Output
$2
per 1M tokens · Standard · < 200k prompt tokens
5.4× the cheapest in view
Coding
49.4
top 50%
Intelligence
24.7
top 28%
Web design
1185 Elo
#83 of 172
Input
$1.25
Cached input
$0.125
Output
$10
per 1M tokens · Standard
14× the cheapest in view
Coding
46.9
Intelligence
14.2
Agentic
7
Input
$1.50
Cached input
—
Output
$7.50
per 1M tokens · Standard
14× the cheapest in view
Coding
42.2
Intelligence
24.9
Agentic
15.5
Input
$1.25
Cached input
$0.20
Output
$2.50
per 1M tokens · Standard · < 200k prompt tokens
6.7× the cheapest in view
Coding
39.7
top 62%
Intelligence
15.2
top 48%
Input
$15
Cached input
$7.50
Output
$60
per 1M tokens · Standard
116× the cheapest in view
Coding
37.8
top 64%
Intelligence
23
top 32%
Web design
1184 Elo
#84 of 172
Input
$1.25
Cached input
$0.125
Output
$10
per 1M tokens · Standard
14× the cheapest in view
AI agents & tools · live prices & stats
Models answer; agents get things done. Plans and prices are read live from each tool's pricing page, popularity from GitHub and real usage — click any tool for the full breakdown.
Describe it, get a working app
You type what you want (“a booking site for my salon”) and the agent writes the code, shows a live preview and can publish it. You refine it by chatting.
Best for: Non-coders, founders validating an idea, quick MVPs and landing pages.
Connect your apps, let AI do the busywork
Visual workflows (“when an email arrives, summarize it with AI and post to Slack”). You drag blocks instead of writing code, and plug an AI model into any step.
Best for: Business owners and teams automating repetitive tasks across tools they already use.
Write code with an AI pair-programmer
A code editor with AI built in: it completes your code, explains errors and can make multi-file changes when you ask. You stay in control of every change.
Best for: People learning to code and developers who want speed without giving up control.
Hand off whole tasks, review the result
Agents that read your whole project, plan, edit many files, run tests and fix failures on their own — usually from the terminal. You review what they did, like a teammate’s pull request.
Best for: Developers shipping features, refactors and bug fixes faster.
Build your own AI agent into your product
Code libraries for building agents yourself: you pick a model, give it tools (search, your database, your APIs) and the framework runs the reasoning loop.
Best for: Developers adding AI assistants, copilots or automated workflows to their own app.
Prices are read live from each tool's pricing page, stars and releases from GitHub, usage from OpenRouter. Click any tool for plans and details.
Usage trends
Real token volume across apps routed through OpenRouter (2026-10-22 – 2026-10-25). Not a survey — what production traffic is choosing right now.
Tokens processed in the latest ranking window.
The tools developers build with every day.
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.
There are many coding agents, but this one is yours.
A coding agent that helps you build and ship with AI
Powerful coding models, funded by ads
Methodology
Straight from each provider's official pricing page, re-checked every few hours. Every model's “All prices” panel links the exact page it came from. If a page changes and our reader breaks, we keep showing the last verified prices and mark the provider below.
We don't run benchmarks and never make up numbers. Intelligence, Coding and Agentic scores are Artificial Analysis's independent indexes; web and UI design scores are Design Arena's crowd-voted Elo ratings; “most used” ranks are real token volume from OpenRouter. Each is linked below.
From the models currently in view: the top performer has the highest score on the benchmark that fits your use case; best value has the most score per dollar among above-median models; the budget pick is the cheapest model that still scores above the median. Change filters or your workload and the picks update.
A model's position in its own provider's lineup, read from the model family (Opus/Sonnet/Haiku, Pro/Flash/Lite, -mini…) and its price. It's a quick orientation aid — for actual quality, use the benchmark scores.
Your monthly input and output tokens × the model's per-million-token prices, with the cached share of input charged at the cache-read rate. It excludes tool fees, search grounding, images and taxes — always confirm on the provider's page before committing budget.
No. It's independent and free to use. No provider pays for placement or rankings.
Independent Intelligence, Coding and Agentic indexes
Crowd-voted Elo for websites, UI components and other design tasks
Real token usage across apps routed through OpenRouter
Community
Every testimonial is verified by hand before it's published.
Reach the developer
Spotted a wrong price, want a provider added, or have an idea that would make this more useful for your team? Partnerships and collaborations are welcome too.
The model that's good enough for your use case can be 10× cheaper than the one you default to. Find yours in a minute.
Your story could be first here.
AgentCost just launched. If it helped you pick a model or cut your AI bill, tell other builders — your words will be the first thing the next visitor reads.