DeepSeek V4.1 Flash 1017
Specifications
- Input
- Output
- Context window
- 1M tokens
- Released
- Oct 2026
Performance
- Speed
- 204 t/s
- TTFT
- 137 ms
- Latency
- 218 ms
- Intelligence
- —
Pricing
- Input
- €0.30 per 1M tokens
- Output
- €1.20 per 1M tokens
About this model
DeepSeek V4.1 Flash 1017 is a minor update to DeepSeek V4.1 Flash, a 552B-parameter multimodal Mixture-of-Experts (MoE) chat model built on the Causal Encoder-Decoder (CED) architecture with compressed KV cache for efficient long-context serving. The update delivers substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks while reducing task execution time and output length, advancing the performance–cost Pareto frontier across multiple agent harnesses. It achieves 42.6 on HLE without tools, 42.3 on Terminal-Bench 4.0, 77.0 on DeepSWE v1.1, and 72.1 on Apex Bench v1.1. The model natively processes images and text, supports a 1M-token context window with up to 256K output tokens, and features thinking mode with numeric reasoning effort control. Available under the MIT license.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- Default On
