S

Apertus 70B Instruct

Sep 2025
SApertus 70B Instruct
Compare in
on
—per task?
$0.88 / $2.08per 1M in / out?
—output speed?
66Kcontext

Ranking?

Alternatives?

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✓ 48 GB GPU · compressed✓ 80 GB GPU · 8-bit
LicenceApache-2.0free for commercial use

Benchmarks

all categories
Chat & Knowledge
GPQA Diamond27.2#306
Coding
Agents & Tool Use
Writing & Language

FAQ

How much does Apertus 70B Instruct cost?›

$0.88 per 1M input tokens and $2.08 per 1M output tokens (cheapest host: Featherless).

Is Apertus 70B Instruct free to use?›

There is no free API; the cheapest paid price is $0.88 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Apertus 70B Instruct, and what is it best at?›

#259 of 334 in Chat & Knowledge, #210 of 239 in Coding, #215 of 242 in Agents & Tool Use, #226 of 245 in Writing & Language.

Is Apertus 70B Instruct better than Gemma 3 270M?›

On AA Intelligence Index 4.3.2, Apertus 70B Instruct scores 5.1 vs 5.1 — about the same.

How can I use Apertus 70B Instruct?›

Through the API of Featherless.

What is the context window of Apertus 70B Instruct?›

66K tokens.

When was Apertus 70B Instruct released? Is there a newer version?›

Released 2025-09-02. It is the current version in its line.

Is Apertus 70B Instruct open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Apertus 70B Instruct locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Apertus 70B Instruct read images?›

No, it accepts text only.

What is Apertus 70B Instruct?›

Apertus 70B Instruct is an open-weights language model from Swiss AI Initiative, released Sep 2025.

What are the best alternatives to Apertus 70B Instruct?›

MiMo v2.6 Pro (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).