N

Nanbeige4.1 3B

Feb 2026
NNanbeige4.1 3B
Compare in
on
—per task?
$0.10 / $0.20per 1M in / out?
—output speed?
256Kcontext

Ranking?

Alternatives?

Run it yourself

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

FAQ

How much does Nanbeige4.1 3B cost?›

$0.10 per 1M input tokens and $0.20 per 1M output tokens (cheapest host: Featherless).

Is Nanbeige4.1 3B free to use?›

There is no free API; the cheapest paid price is $0.10 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Nanbeige4.1 3B, and what is it best at?›

#177 of 334 in Chat & Knowledge, #210 of 239 in Coding, #122 of 175 in Agents & Tool Use, #181 of 245 in Writing & Language.

Is Nanbeige4.1 3B better than GPT-4o?›

On AA Intelligence Index 4.3.2, Nanbeige4.1 3B scores 8.4 vs 8.4 — about the same.

How can I use Nanbeige4.1 3B?›

Through the API of Featherless.

What is the context window of Nanbeige4.1 3B?›

256K tokens.

When was Nanbeige4.1 3B released? Is there a newer version?›

Released 2026-02-11. It is the current version in its line.

Is Nanbeige4.1 3B open source?›

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

Can I run Nanbeige4.1 3B locally?›

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

Can Nanbeige4.1 3B read images?›

No, it accepts text only.

What is Nanbeige4.1 3B?›

Nanbeige4.1 3B is an open-weights language model from Nanbeige, released Feb 2026.

What are the best alternatives to Nanbeige4.1 3B?›

Ling 3.0 Flash VL (cheaper), GPT-6 Luna (better), K2 Horizon 7B (open weights).