This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Institute of Foundation Models has launched a newer release, K2 Horizon 375B A23B. We suggest considering it instead.
K2-V2: Intelligence, Performance & Price Analysis
Model summary
Performance
Verbosity
K2-V2 (High) supports text input, outputs text, and has a 512k tokens context window.
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 512k ~768 A4 pages of size 12 Arial font |
| Total parameters | 70B |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Time per Task
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
More from Institute of Foundation Models
Frequently Asked Questions
Common questions about K2-V2
K2-V2 was released on December 5, 2025.
K2-V2 was created by Institute of Foundation Models.
Yes, K2-V2 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
K2-V2 supports text input.
K2-V2 supports text output.
No, K2-V2 does not support image input. It can only process text.
No, K2-V2 is not multimodal. It only supports text input.
K2-V2 has a context window of 512k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, K2-V2 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
K2-V2 has 70B parameters.
K2-V2 is released under the Apache 2.0 license. This license allows commercial use. View license
K2-V2 is an open weights model that can be self-hosted. View providers
K2-V2 is an open weights model that can be downloaded and self-hosted. Compare providers