DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks.
The model merges pretrained weights from both source models to balance performance across reasoning, efficiency, and instruction-following tasks. It is released under the MIT license and intended for research and commercial use.
Modalities
Price
Free
Context
164K
Released
Apr 27, 2025
Knowledge Cutoff
Jul 2024
Token volume and request traffic to this model over time.
DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks.
Yes. The pricing shown on this page for DeepSeek R1T Chimera is zero, so you are not charged for prompt or completion tokens. Free endpoints are rate limited — see the rate limit docs.
DeepSeek R1T Chimera has a 163,840 token context window.
DeepSeek R1T Chimera was released on April 27, 2025. Its knowledge cutoff is July 31, 2024.