This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Arctic Instruct: Intelligence, Performance & Price Analysis
Model summary
Performance
Verbosity
Arctic Instruct supports text input, outputs text, and has a 4k tokens context window.
| Reasoning | No |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 4k ~6 A4 pages of size 12 Arial font |
| Total parameters | 480B |
| Active parameters | 17B Number of parameters active per token during inference |
| 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
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Arctic Instruct | - | 480B 17B active at inference time | 4k | - | - | - | - |
Frequently Asked Questions
Common questions about Arctic Instruct
Arctic Instruct was released on April 24, 2024.
Arctic Instruct was created by Snowflake.
No, Arctic Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Arctic Instruct supports text input.
Arctic Instruct supports text output.
No, Arctic Instruct does not support image input. It can only process text.
No, Arctic Instruct is not multimodal. It only supports text input.
Arctic Instruct has a context window of 4k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Arctic Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Arctic Instruct has 480B parameters (17B active).
Arctic Instruct is a Mixture of Experts (MoE) model with 480B total parameters, but only 17B active parameters are used during inference.
Arctic Instruct is released under the Apache 2.0 license. This license allows commercial use. View license
Arctic Instruct is an open weights model that can be self-hosted. View providers
Arctic Instruct is an open weights model that can be downloaded and self-hosted. Compare providers