DeepSeek-V4.1-Flash
- In Input modalities: TextImage Out Output modalities: Text
- Reasoning· low, high, max
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
11 offerings · prices as listed DeepSeek API (opens in a new tab)
deepseek-flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Peak hours Standard | $0.30 | $0.006 | $1.20 |
| Off-peak hours | $0.15 | $0.003 | $0.60 |
When it applies, as the source states: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.
Prices from DeepSeek API models & pricing (opens in a new tab) (checked Nov 9, 2026)
DeepSeek API (opens in a new tab)
deepseek-flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Peak hours Standard | ¥2.00 | ¥0.040 | ¥8.00 |
| Off-peak hours | ¥1.00 | ¥0.020 | ¥4.00 |
Prices from DeepSeek API：模型 & 价格 (opens in a new tab) (checked Nov 8, 2026)
Volcengine Ark (opens in a new tab)
deepseek-v4-1-flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Flex tier | ¥1.00 | ¥0.020 | ¥4.00 |
| Peak hours Standard | ¥2.00 | ¥0.040 | ¥8.00 |
| Off-peak hours | ¥1.00 | ¥0.020 | ¥4.00 |
| Batch | ¥1.00 | ¥0.020 | ¥4.00 |
Prices from 火山方舟：模型价格 (opens in a new tab) (checked Nov 6, 2026)
Alibaba Cloud Model Studio (opens in a new tab)
deepseek-v4.1-flash| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Peak hours Standard | $0.30 | $1.20 |
| Off-peak hours | $0.15 | $0.60 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026)
Alibaba Cloud Model Studio (opens in a new tab)
deepseek-v4.1-flash| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Peak hours Standard | $0.283 | $1.131 |
| Off-peak hours | $0.141 | $0.565 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026)
Alibaba Cloud Model Studio (opens in a new tab)
deepseek-v4.1-flash| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥2.00 | ¥8.00 |
| Off-peak hours | ¥1.00 | ¥4.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Nov 9, 2026)
Alibaba Cloud Model Studio (opens in a new tab)
vanchin/deepseek-v4.1-flash| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥2.00 | ¥8.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Nov 9, 2026)
Alibaba Cloud Model Studio (opens in a new tab)
deepseek-v4.1-flash| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Peak hours no longer listed since Oct 23, 2026 | $0.283 | $1.131 |
| Off-peak hours no longer listed since Oct 23, 2026 | $0.141 | $0.565 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Built-in tools
- Web search
- Knowledge cutoff
- May 2025
- Licence
- MIT License
- Family
- deepseek-flash
- Aliases
- deepseek-v4-flash, deepseek-v4-flash-vision-exp
- Model ID
Not stated on DeepSeek’s pages: max input, max thinking budget.
Run locally
Weights: deepseek-ai/DeepSeek-V4.1-Flash- Parameters 763.2B
- Active 228.1B (estimated) · 384 experts, 6 per token
- Native precision FP8
- Layers 40
- KV cache per token 80 KB
- Config positions 1024K (config.json max_position_embeddings)
- API context 977K (maker’s API)
On your hardware · GeForce RTX 4090
✕Doesn’t fit IQ4_XS (automatic) 8K context
WeightsKV cacheOverheadUsable
- Needs
- ≈ 397.1 GB (weights 377.6 + KV cache 0.6 + overhead 18.9)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| FP8 (native)maker’s file | 475.3 GB | ≈ 499.6 | ✕Doesn’t fit | — |
| Q6_K | 583.7 GB | ≈ 613.5 | ✕Doesn’t fit | — |
| Q5_K_M | 505.5 GB | ≈ 531.5 | ✕Doesn’t fit | — |
| Q5_0 | 488.7 GB | ≈ 513.7 | ✕Doesn’t fit | — |
| Q4_K_M | 431.8 GB | ≈ 454.0 | ✕Doesn’t fit | — |
| Q4_0 | 399.8 GB | ≈ 420.4 | ✕Doesn’t fit | — |
| IQ4_XS | 377.6 GB | ≈ 397.1 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 347.4 GB | ≈ 365.4 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 271.9 GB | ≈ 286.1 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 266.5 GB | ≈ 280.5 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 183.0 GB | ≈ 192.8 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed machine; about 7 × 80 GB GPUs.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Full≈ 11375.2 GBDoesn’t fit your hardware
LoRA≈ 1425.0 GBDoesn’t fit your hardware
QLoRA≈ 403.2 GBDoesn’t fit your hardware
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-11. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 156.5
#33 of 118 listed models · CI 154.6–158.6
- Epoch AI · Chess Puzzles 48%
#21 of 85 listed models · max effort · ±5.02
- Epoch AI · FrontierMath Tier 4 v2 26.8%
#36 of 65 listed models · max effort · ±7.01
- Epoch AI · FrontierMath Tiers 1–3 67.4%
#31 of 84 listed models · max effort · ±2.78
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 28 – Nov 5, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 28, 2026
- LiveBench (White et al.), release 2026-06-25, livebench.ai, licensed CC BY-SA 4.0. This board, adapted from it, is shared under CC BY-SA 4.0. · License · as of Jun 25, 2026
- changes we made
Provider-reported scores
Published by DeepSeek, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| GPQA Diamond | pass@1, max reasoning effort | 90.9% |
| Humanity's Last Exam | pass@1, no tools, max reasoning effort | 36.8% |
| pass@1, no tools, text-only subset, max reasoning effort | 39.1% | |
| pass@1, with tools, max reasoning effort | 63.9% | |
| Terminal-Bench 2.1 | pass@1, DeepSeek Harness Minimal mode, max reasoning effort | 90.6% |
Included in coding plans
- 5× the usage of the Lite plan
- TRAE Free Free500 credits per month
News
All news →- Oct 17, 2026Release DeepSeek upgrades V4.1 Flash to version 1017 DeepSeek upgraded DeepSeek V4.1 Flash to DeepSeek-V4.1-Flash-1017; developers can access it using deepseek-flash, with the API method and pricing unchanged.
- Sep 10, 2026Release DeepSeek releases DeepSeek-V4.1-Flash DeepSeek released DeepSeek-V4.1-Flash, its smallest new-architecture model with native multimodal vision, callable as deepseek-flash. The retired names deepseek-v4-flash and deepseek-v4-flash-vision-exp route to it for now. V4 Pro continues after 14 September 2026 with unchanged billing, and API prices were reduced with the release.
Changes
All changes →- 6 new prices on Volcengine Ark, China Input (Flex tier) ¥1.00 · Cache read (Flex tier) ¥0.020 · Output (Flex tier) ¥4.00 · Input (Batch) ¥1.00 · +2 more
- 12 new prices on Volcengine Ark, China Input (Flex tier, Off-peak hours) ¥0.50 · Cache read (Flex tier, Off-peak hours) ¥0.020 · Output (Flex tier, Off-peak hours) ¥2.00 · Input (Flex tier, Peak hours) ¥1.00 · +8 more
- Now priced on SiliconFlow, China Input (Peak hours) ¥2.00 · Output (Peak hours) ¥8.00 · Cache read (Peak hours) ¥0.040 · Input (Off-peak hours) ¥1.00 · +2 more
- Now priced on Alibaba Cloud Model Studio, China Input ¥2.00 · Output ¥8.00
- Now priced on Alibaba Cloud Model Studio, China Input ¥2.00 · Input (Off-peak hours) ¥1.00 · Output ¥8.00 · Output (Off-peak hours) ¥4.00
- No longer priced on Alibaba Cloud Model Studio, International Input $0.20 · Output $0.40 · Cache read $0.040
- No longer priced on Alibaba Cloud Model Studio Input $0.138 · Output $0.275 · Cache read $0.028
- 3 prices dropped on Volcengine Ark, cn-beijing Input (Flex tier) ¥1.50 · Cache read (Flex tier) ¥0.10 · Output (Flex tier) ¥4.50
- Now priced on Alibaba Cloud Model Studio, China Input ¥1.00 · Output ¥2.00
- Now priced on SiliconFlow, China Input (Off-peak hours) ¥1.50 · Output (Off-peak hours) ¥4.50 · Cache read (Off-peak hours) ¥0.15 · Input (Peak hours) ¥3.00 · +2 more
- Now priced on Alibaba Cloud Model Studio, International Input $0.20 · Output $0.40 · Cache read $0.040
- Now priced on Alibaba Cloud Model Studio Input $0.138 · Output $0.275 · Cache read $0.028
- 3 new prices on Volcengine Ark, cn-beijing Input (Flex tier) ¥1.50 · Cache read (Flex tier) ¥0.10 · Output (Flex tier) ¥4.50
- Now priced on Volcengine Ark, cn-beijing Input (Off-peak hours) ¥1.00 · Cache read (Off-peak hours) ¥0.020 · Output (Off-peak hours) ¥4.00 · Input (Peak hours) ¥2.00 · +2 more
- 3 new prices on DeepSeek API Cache read (Peak hours) $0.006 · Input (Peak hours) $0.30 · Output (Peak hours) $1.20
- New language model
Sources
- DeepSeek-V4.1-Flash model card (Hugging Face, deepseek-ai) (opens in a new tab) huggingface.co · checked Sep 26, 2026
- DeepSeek API models & pricing (opens in a new tab) api-docs.deepseek.com · checked Nov 9, 2026
- DeepSeek API：模型 & 价格in Chinese (opens in a new tab) api-docs.deepseek.com · checked Nov 8, 2026
- 火山方舟：模型价格in Chinese (opens in a new tab) docs.volcengine.com · checked Nov 6, 2026
- DeepSeek API change log (opens in a new tab) api-docs.deepseek.com · checked Nov 9, 2026
- deepseek-ai/DeepSeek-V4.1-Flash model card (opens in a new tab) huggingface.co · checked Nov 9, 2026
- models.dev: deepseek/deepseek-v4.1-flash (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- DeepSeek | Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. (opens in a new tab) deepseek.com · checked Nov 8, 2026
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Nov 9, 2026
- Explore Qwen3, Wan2.6 & Latest Models on Model Studio - Alibaba Cloud Model Studio - Alibaba Cloud_Alibaba Cloud Model Studio(Model Studio) - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center (opens in a new tab) alibabacloud.com · checked Nov 9, 2026
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression (opens in a new tab) huggingface.co · checked Nov 9, 2026
- DeepSeek (opens in a new tab) alibabacloud.com · checked Nov 8, 2026
- DeepSeek API Docs (opens in a new tab) api-docs.deepseek.com · checked Nov 7, 2026
- 阿里云百炼：模型价格in Chinese (opens in a new tab) help.aliyun.com · checked Nov 9, 2026
- 模型上下架与更新-大模型服务平台百炼-阿里云_大模型服务平台百炼(Model Studio)-大模型服务平台百炼(Model Studio)-阿里云帮助中心in Chinese (opens in a new tab) help.aliyun.com · checked Nov 4, 2026
- deepseek-ai/DeepSeek-V4.1-Flash model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- deepseek-ai/DeepSeek-V4.1-Flash config.json (opens in a new tab) huggingface.co · checked Nov 3, 2026
- deepseek-ai/DeepSeek-V4.1-Flash files (opens in a new tab) huggingface.co · checked Nov 6, 2026
- 硅基流动：模型价格in Chinese (opens in a new tab) siliconflow.cn · checked Nov 6, 2026
- DeepSeek | 深度求索in Chinese (opens in a new tab) deepseek.com · checked Nov 6, 2026
DeepSeek’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
DeepSeek · China · deepseek.com
Related models
Snapshots, the same family and other models from this provider