Skip to content
FullsendAI
Log inGet started

Methodology

How we compare providers

We make FullsendAI, and we compare it with other providers. These are the rules those pages follow, so you can check our work.

Get your API keySee our pricingLast verified Oct 15, 2026

The rules

Every fact has a source and a date

Each fact about another provider links to the page or API it came from and shows the day we checked it. We use providers' own pricing pages, docs, terms and public APIs; press coverage only for company news such as an acquisition, and third-party price trackers never.

Prices are compared like for like

Same model and version on every side. A promotion counts while it runs and is labelled. For OpenRouter we show the price most of its providers charge for the model and the lowest-priced endpoint with its precision, from its public endpoints API. Fees are added in the worked examples, with the arithmetic shown. Cache and batch discounts are left out of the examples and named in the tables.

Our own prices are live

FullsendAI's prices come from our catalogue when the page is built, never typed by hand. A model we don't serve yet shows as not offered.

Nothing stale is shown as current

A price older than 30 days, or any other fact older than 90, is replaced by a link to the provider's own page. The “last verified” date at the top of each page is the oldest check date among the facts on it.

Refreshed weekly

Each week we read the public price APIs of OpenRouter, DeepInfra and Requesty. A price that moved by less than half is updated; a bigger move, a model that disappeared, or any change to a watched pricing or policy page goes to a person to review before the page changes.

Fair to the other side

Every comparison says when the other provider is the better choice, and we don't make unscoped claims like “cheapest” or “fastest”. Names are plain text: no logos, brand colours or screenshots.

Corrections

If something here is wrong or out of date, email [email protected] with the page and the source. We check every report and correct the page, with the new check date shown.

Sources we check

Each provider's pages and APIs we read, with how and when.

OpenRouter

DeepInfra

Requesty

Portkey

Together AI

Fireworks AI

Groq

Unify

Related comparisons

One key. Every model. No top-up fee.

Works with the OpenAI and Anthropic SDKs, Claude Code, Codex and other coding agents. Every model runs in the USA.

Get your API keyRead the quickstart

OpenRouter, Requesty, Portkey, DeepInfra, Together AI, Fireworks AI, Groq, Unify, OpenAI, Anthropic, Claude, Google, Gemini and DeepSeek are trademarks of their respective owners. FullsendAI is not affiliated with, endorsed by or sponsored by any of them; names are used only to identify the products compared.

Based on publicly available information as of the dates shown; features and prices change. How we compare · Report an inaccuracy