OpenRouter

OpenRouter — One OpenAI-shaped key in front of hundreds of models. OpenRouter aggregates nearly every model in this category behind a single OpenAI-compatible endpoint, with automatic failover between upstream hosts, per-provider routing preferences and privacy filters that exclude hosts who train on prompts. You pay upstream rates plus a credit fee. It is the cheapest way to keep model choice a runtime decision instead of an architectural one. Founded 2023.

We track it in 1 comparison — LLM APIs — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 17 other tools, and what follows is where it visibly separates from them.

Where it gives ground.

• Batch discount — 0 %, 8th of 10. Anthropic records 50 %.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 19 of 27 tracked fields carry a value for OpenRouter, and 2 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is Qwen. Qwen takes Batch discount (50 % against 0 %) and Trains on your data (Partial against No). That pattern repeats across the rest of the roster — see OpenRouter alternatives for the other rivals, each compared the same way.

Founded

2023

Fields we track

19 of 27

Last verified

2026-01-15

The highest-leverage integration in the category: one endpoint, hundreds of models, automatic failover, and privacy filters that let you exclude hosts who train on prompts. The trade is that you get the intersection of upstream features, not the union — no batch, no computer use, and caching only where it passes through.

Batch discount

0 %8th of 10

Inferredverified 2026-01-15

Tool use

●Yes1st of 18

Inferredverified 2026-01-15

Trains on your data

○No7th of 18

Inferredverified 2026-01-15

OpenAI-compat API

●Yes1st of 18

Vendor-claimedverified 2026-01-15source

MCP support

○No6th of 18

Inferredverified 2026-01-15

AU region

○No8th of 17

Inferredverified 2026-01-15

Computer use

○No5th of 18

Inferredverified 2026-01-15

Pinnable versions

◐Partial14th of 18

Inferredverified 2026-01-15

OpenRouter is the right call in these situations, each one drawn from a field we actually record:

• Keeping model choice a runtime decision rather than an architectural one.
• Benchmarking a dozen models without a dozen accounts.
• Failover when a single upstream host goes down.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• Batch discount. OpenRouter records 0 %, 8th of 10 in the LLM APIs roster. Anthropic records 50 % on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 8 of the 27 fields we track for OpenRouter are still blank: Context window, Max output, TTFT p50, Output tok/s, $/M input, $/M output, $/M cache read and Notice period. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.