Read the market
like paper.
Registry 10 models · Refresh weekly · Sponsored none
Every major LLM API — input, output and cached-token prices per 1M tokens, context windows and capabilities. Verified against official pages, refreshed weekly, free forever.
Models tracked
10
▲ open + closed weights
Min input $/1M
$0.15
▼ cheapest verified rate
Max context
1.05M
▲ tokens in one window
Providers
08
▲ official sources only
Cheapest right now
updated Nov 1, 2025| # | Model | Input $/1M | Output $/1M |
|---|---|---|---|
| 01 | DeepSeek V3.2 Open | $0.28 | $0.42 |
| 02 | DeepSeek V3.2 Open | $0.3 | $0.45 |
| 03 | Llama 4 Maverick Open | $0.15 | $0.6 |
| 04 | Llama 4 Maverick Open | $0.2 | $0.6 |
| 05 | GPT-5 mini Closed | $0.25 | $2.00 |
Tools
T/01
Pricing
Full table of model × provider prices per 1M tokens. Sort, filter by capability, check freshness.
T/02
Calculator
Plug in your traffic — requests per day and token volumes — and get the monthly bill per model.
T/03
Guides
Practical guides: how to compare API pricing, cut costs with caching, pick a model for a task.
How it works
Data lives in git
Every model and price is a JSON file in a public repo. Full history, diffs and review via pull requests.
Weekly bots
Automated jobs re-check official pricing pages every week and open PRs with changes — humans approve.
Every number has a source
Each price links to the official provider page and carries an updatedAt date. No unsourced numbers, ever.
Digest
Price-change digest
One short email when a major provider changes API prices. No spam, unsubscribe anytime.