DeepSeek V4.1 Flash
DeepSeek· released 10 Sept 2026
deepseek/deepseek-v4.1-flash- Input / 1M tokens
- $0.3
- Output / 1M tokens
- $1.2
Longest answer: 944K tokens
About
DeepSeek V4.1 Flash is an open-weights model from DeepSeek built on its Causal Encoder-Decoder architecture. It is a sparse mixture-of-experts model, with 8 billion parameters activated on input and 16 billion on output, according to its listed summary. It accepts text and images and returns text. The model supports tools, vision, and reasoning, with a 1,048,576-token context window and a maximum output of 943,718 tokens. Its Hugging Face ID is deepseek-ai/DeepSeek-V4.1-Flash, and its model ID is deepseek/deepseek-v4.1-flash. It was released on 2026-09-10. Pricing is USD 0.3 per 1 million input tokens and USD 1.2 per 1 million output tokens. Builders can consider its open weights, multimodal input, and tool support alongside the unusually large listed context and output limits when matching it to tasks.
Who it is for
DeepSeek V4.1 Flash may suit builders seeking open weights, image input, and tool support in a model with a very large context window. Its reasoning support may also fit workflows involving multi-step tasks.
What is good
- Open weights
- 1,048,576-token context window
- Accepts text and image inputs
- Supports tools and reasoning
What to know first
- Input costs USD 0.3 per 1M tokens
- Output costs USD 1.2 per 1M tokens
Verdict
DeepSeek V4.1 Flash brings open weights, image input, and tool support together with a large context window. Its token rates and stated maximum output provide clear parameters for teams considering it for their stack.
Details
- Lab
- DeepSeekopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.3 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $1.2 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 943,718 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, imageopenrouter.ai · 3 Oct 2026
- Open weights
- Yesopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Open-Weight Models in 2026178 listed
- DeepSeek Models: Pricing per 1M Tokens and Context (2026)18 listed
Sources
- openrouter.ai/deepseek/deepseek-v4.1-flash· checked 3 Oct 2026