K2-Horizon 7B (FP8, reasoning + tools)
K2-Horizon 7B is a fully open dense 7B-class model from IFM (Apache 2.0, September 2026): training data, recipe and intermediate checkpoints are public, and specialist models for maths, code, search and tool use were merged into the final weights. English only, with three levels of reasoning effort. Its value is transparency — a reproducible baseline for research rather than a production workhorse. The model is currently offline; the card stays for reference.
model id: k2-horizon-7b
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="k2-horizon-7b", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "k2-horizon-7b", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "k2-horizon-7b", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- IFM
- Released
- September 2026
- Licence
- Apache-2.0
- Architecture
- dense
- Input
- text
- Reasoning
- selectable effort
- Languages named by the developer
- English
Source: the developer's model card, as of 17 September 2026.
Licence: what it means for your company
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
A summary of the licence, not legal advice.
Technical details
- Context window
- 128K tokens
- Max output
- 16,384 tokens
- Throughput limit
- 1.5M tok/min
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- IFM/K2-Horizon-7B
- max_tokens
- 1 … 16384
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.
Questions about this model
›Where is K2-Horizon 7B computed?
Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.
›Does K2-Horizon 7B store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the K2-Horizon 7B context window?
128K tokens, with up to 16,384 tokens of output.
›What does K2-Horizon 7B cost?
This model is quoted on request — write to us and we will price it for your volume.
›Is there a throughput limit on K2-Horizon 7B?
Yes, 1.5M tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does K2-Horizon 7B support?
The developer names English. Languages not on that list may still work, but they are not claimed — test on your own material first.
›Under which licence is K2-Horizon 7B released?
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
›Can reasoning be switched off in K2-Horizon 7B?
The developer lets you choose how much the model reasons; the card does not document turning reasoning off completely.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| K2-Horizon 7B (FP8, reasoning + tools) | IFM | — | 128K | Apache-2.0 | on request |
| GLM-5.3-Flash (NVFP4) | Z.ai | 320B / 18B | 1M | MIT | $0.04 |
| gpt-oss-20b | OpenAI | 21B / 3.6B | 128K | Apache-2.0 | $0.05 |
| Mistral Small 24B (2501) | Mistral AI | 24B | 32K | Apache-2.0 | $0.05 |
30 more models behind the same key and the same invoice.
Browse the catalog