DeepSeek V4.1-Flash — Specifications
Compiled by Mustafa Ihsan from the vendor’s published documentation · Last updated
| Developer | DeepSeek |
|---|---|
| Type | LLM (MoE, multimodal) |
| Modality | Text, Vision → Text |
| Parameters | 552B total (MoE; 8B active for input, 16B for output) |
| Context window | 1M |
| Max output | 384K |
| License | MIT (open) |
| Open weights | Yes |
| Released | 2026-09 |
| Input price | $0.30 /1M |
| Output price | $1.20 /1M |
| API providers | DeepSeek API (deepseek-flash), Alibaba Cloud Model Studio, OpenRouter |
Benchmarks
| DeepSeek-reported (V4.1-Flash-1017, 17 Oct 2026) | HLE 42.6 (no tools); Terminal-Bench 4.0 42.3; DeepSWE v1.1 77.0; ProgramBench 29.1. Prices shown are peak rates; off-peak is half. |
|---|
What is DeepSeek V4.1-Flash?
DeepSeek V4.1-Flash is DeepSeek’s current Flash model, called deepseek-flash on its API. DeepSeek released it on 10 September 2026 as the smallest model in a new architecture family: a 552B-parameter mixture-of-experts whose causal encoder–decoder design activates 8B parameters for input and 16B for output, with native visual understanding. On 17 October 2026 DeepSeek shipped an update, DeepSeek-V4.1-Flash-1017, which now serves every deepseek-flash call at the same price. The weights are on Hugging Face under the MIT licence, a download of about 510 GB.
DeepSeek bills peak and off-peak rates. At peak it costs $0.30 per million input tokens (cache miss), $0.006 per million cached input tokens and $1.20 per million output tokens; off-peak rates are half that ($0.15 in, $0.003 cached, $0.60 out). Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays; weekends are off-peak all day. The table on this page shows the peak price. The model has a 1M-token context window and up to 384K output tokens, thinks by default (a non-thinking mode is available) and accepts both OpenAI and Anthropic request formats.
V4.1-Flash replaced DeepSeek V4-Flash, which DeepSeek retired on 10 September 2026; the old deepseek-v4-flash name is still accepted and served by V4.1-Flash-1017. DeepSeek says V4.1-Flash scores ahead of its larger DeepSeek V4-Pro on benchmarks, while V4-Pro costs $1.32 in / $3.96 out at peak and takes no image input. All DeepSeek rates are on our DeepSeek API pricing page, and the AI API cost calculator turns them into a monthly bill.
DeepSeek V4.1-Flash pricing: API cost per 1M tokens
| Input (per 1M tokens) | $0.300 |
|---|---|
| Output (per 1M tokens) | $1.20 |
| Output/input ratio | 4× |
| Blended (4:1 in:out) | $0.480 per 1M tokens |
What DeepSeek V4.1-Flash costs per month
Real monthly spend at a 4:1 input-to-output mix — the ratio a typical chat or RAG workload actually produces.
| Workload | Tokens / month | Cost / month |
|---|---|---|
| Side project | 1M in / 0.25M out | $0.60 |
| Small team | 20M in / 5M out | $12 |
| Production | 200M in / 50M out | $120 |
Run your own numbers in the AI API cost calculator.
Cheaper alternatives to DeepSeek V4.1-Flash
| Model | Blended $/1M | You save |
|---|---|---|
| Llama 3.1 8B open | $0.0240 | 95% cheaper |
| Mistral NeMo 12B open | $0.0292 | 94% cheaper |
| Gemma 3 4B open | $0.0600 | 88% cheaper |
Frequently asked questions
How much does DeepSeek V4.1-Flash cost per 1M tokens?
DeepSeek V4.1-Flash costs $0.300 per 1M input tokens and $1.20 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $0.480 per 1M tokens.
How much does DeepSeek V4.1-Flash cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $12 on DeepSeek V4.1-Flash. A side project (1M in / 0.25M out) costs roughly $0.60.
What is a cheaper alternative to DeepSeek V4.1-Flash?
Llama 3.1 8B is the strongest cheaper option in our database at $0.0240 per 1M blended — about 95% less than DeepSeek V4.1-Flash. It is also open-weight, so self-hosting is an option.
Can I run DeepSeek V4.1-Flash locally?
Yes. DeepSeek V4.1-Flash is open-weight and needs about a large amount of VRAM at 4-bit quantisation.
Why does DeepSeek V4.1-Flash charge more for output than input?
Output tokens are generated one at a time and cannot be batched the way a prompt can, so they cost the provider more to serve. DeepSeek V4.1-Flash charges 4× more for output, which is why prompt-heavy workloads are far cheaper to run than generation-heavy ones.
See every DeepSeek model priced side by side: DeepSeek API pricing.
Prices are the published list rates for the model's primary API and are reviewed as providers change them. Volume, batch and cached-input discounts are not included. Compare every model side by side in the AI models database or the LLM leaderboard.