I

K2 Horizon 7B

Sep 2026
IK2 Horizon 7B
Compare in
on
—per task?
$0.30 / $1.20per 1M in / out?
—output speed?
524Kcontext

Alternatives?

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 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 K2 Horizon 7B cost?›

$0.30 per 1M input tokens and $1.20 per 1M output tokens (cheapest host: Featherless).

Is K2 Horizon 7B free to use?›

There is no free API; the cheapest paid price is $0.30 per 1M input tokens. The weights are open, so you can run it yourself.

How good is K2 Horizon 7B, and what is it best at?›

#131 of 334 in Chat & Knowledge, #54 of 132 in Coding, #59 of 133 in Agents & Tool Use, #99 of 133 in Vision & Documents.

Is K2 Horizon 7B better than Claude Sonnet 4.6?›

On AA-Briefcase 1.1 · Elo, K2 Horizon 7B scores 1,015.6 vs 1,063 — lower.

How can I use K2 Horizon 7B?›

Through the API of Featherless.

What is the context window of K2 Horizon 7B?›

524K tokens.

When was K2 Horizon 7B released? Is there a newer version?›

Released 2026-09-03. It is the current version in its line.

Is K2 Horizon 7B open source?›

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

Can I run K2 Horizon 7B locally?›

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

Can K2 Horizon 7B read images?›

No, it accepts text only.

What is K2 Horizon 7B?›

K2 Horizon 7B is an open-weights language model from Institute of Foundation Models, released Sep 2026.

What are the best alternatives to K2 Horizon 7B?›

Qwen3.8 Flash (cheaper), GPT-6 Luna (better), K2 Horizon 3.7B (open weights).