DeepSeek V4.1 Flash
Fast and lightVisionToolsDeepSeek · Released September 2026
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 is part of DeepSeek's open-weight line, known for delivering near-frontier reasoning and coding quality at a fraction of typical frontier pricing, with V4.1 Flash at the head and the V4 Pro and Flash tiers behind it.
Facts and pricing
- Provider
- DeepSeek
- Context window
- 1.0M tokens
- Input price
- 3.6 credits / 1M tokens ($0.30 raw)
- Output price
- 14.4 credits / 1M tokens ($1.20 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try DeepSeek V4.1 Flash now
What DeepSeek V4.1 Flash is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
- Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a fast and light model like DeepSeek V4.1 Flash:
- Summarize this article in five bullet points
- Rewrite this email to be shorter and friendlier
- Give me ten name ideas for a hiking newsletter
- Translate this paragraph to Spanish and keep the tone
DeepSeek family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1.0M | 3.6 | 14.4 | September 2026 |
| DeepSeek V4.1 Flash (batch) | 1.0M | 1.3 | 4.0 | September 2026 |
| DeepSeek V4 Flash Vision Exp | 1.0M | 2.6 | 7.8 | August 2026 |
| DeepSeek V4 Pro 0813 | 1.0M | 7.9 | 23.8 | August 2026 |
| DeepSeek V4 Flash 0731 | 1.0M | 0.22 | 15.4 | July 2026 |
| DeepSeek V4 Pro 0423 | 1.0M | 2.5 | 5.0 | April 2026 |
| DeepSeek V4 Flash 0423 | 1.0M | 0.36 | 15.4 | April 2026 |
| DeepSeek V3.2 | 131K | 3.4 | 5.0 | December 2025 |
| DeepSeek V3.2 Exp | 164K | 3.2 | 4.9 | September 2025 |
| DeepSeek V3.1 Terminus | 164K | 3.2 | 12.0 | September 2025 |
Frequently asked questions
- What is DeepSeek V4.1 Flash?
- DeepSeek V4.1 Flash is an AI model by DeepSeek. 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.
- How much does DeepSeek V4.1 Flash cost on Zeplik?
- Input tokens cost 3.6 credits per million and output tokens 14.4 credits per million (1 credit = $0.10; the raw provider rates are $0.30 and $1.20 per million). New accounts start with free credits.
- How long can a conversation with DeepSeek V4.1 Flash be?
- DeepSeek V4.1 Flash has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.
- Does DeepSeek V4.1 Flash support images and tools?
- DeepSeek V4.1 Flash accepts image input and supports tool calling.
Related models
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.
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
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.
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.
More you can do with DeepSeek V4.1 Flash
- 467 AI skillsReady-to-run expert methods for writing, data, code and more, each running on DeepSeek V4.1 Flash or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.