DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
70 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
23 providers
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
71 providers
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
68 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | DeepSeek |
65.6 | 1.04858M | $0.02 | $1 | 2026-09-10 | ||
| Tencent: Hy3tencent/hy3 | Tencent |
38.7 | 262.144K | $0.083 | $0.33 | 2026-07-06 | ||
| DeepSeek: DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | DeepSeek |
38.3 | 1.024M | $0.209 | $0.418 | 2026-04-24 | ||
| DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | DeepSeek |
33.0 | 1.04858M | $0.091 | $0.182 | 2026-04-24 |