DeepSeek-V4-Pro
- In Input modalities: Text Out Output modalities: Text
- Reasoning· low, high, max
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
13 offerings · prices as listeddeepseek-v4-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Peak hours Standard | $1.32 | $0.044 | $3.96 |
| Off-peak hours | $0.66 | $0.022 | $1.98 |
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-v4-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Peak hours Standard | ¥9.00 | ¥0.30 | ¥27.00 |
| Off-peak hours | ¥4.50 | ¥0.15 | ¥13.50 |
Prices from DeepSeek API：模型 & 价格 (opens in a new tab) (checked Nov 8, 2026)
deepseek-v4-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥9.00 | ¥0.30 | ¥27.00 |
| Flex tier | ¥4.50 | ¥0.30 | ¥13.50 |
| Batch | ¥4.50 | ¥0.30 | ¥13.50 |
Prices from 火山方舟：模型价格 (opens in a new tab) (checked Nov 9, 2026)
deepseek-v4-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $2.40 | $0.20 | $4.80 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026) · DeepSeek V4 Pro model (opens in a new tab) (checked Nov 9, 2026)
deepseek-v4-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $1.65 | $0.138 | $3.301 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026) · DeepSeek V4 Pro model (opens in a new tab) (checked Nov 9, 2026)
deepseek-v4-pro| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥12.00 | ¥24.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Nov 9, 2026)
vanchin/deepseek-v4-pro| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥12.00 | ¥24.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Nov 9, 2026)
deepseek-v4-pro| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | — | $3.301 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026)
deepseek-v4-pro| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | — | $3.30 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026)
deepseek-v4-pro| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | $2.40 | $4.80 |
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
- Knowledge cutoff
- May 2025
- Licence
- MIT License
- Family
- deepseek-pro
- Model ID
Not stated on DeepSeek’s pages: max input, max thinking budget, built-in tools, aliases.
Run locally
Weights: deepseek-ai/DeepSeek-V4-Pro- Parameters 1.6T
- Active 49B · 384 experts, 6 per token
- Native precision FP8
- Layers 61
- KV cache per token 122 KB
- Config positions 1024K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 831.6 GB (weights 791.1 + KV cache 1.0 + overhead 39.6)
- 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 | 805.3 GB | ≈ 846.6 | ✕Doesn’t fit | — |
| Q6_K | 1222.9 GB | ≈ 1285.0 | ✕Doesn’t fit | — |
| Q5_K_M | 1059.1 GB | ≈ 1113.0 | ✕Doesn’t fit | — |
| Q5_0 | 1023.7 GB | ≈ 1075.9 | ✕Doesn’t fit | — |
| Q4_K_M | 904.6 GB | ≈ 950.8 | ✕Doesn’t fit | — |
| Q4_0 | 837.6 GB | ≈ 880.4 | ✕Doesn’t fit | — |
| IQ4_XS | 791.1 GB | ≈ 831.6 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 727.8 GB | ≈ 765.1 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 569.6 GB | ≈ 599.0 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 558.4 GB | ≈ 587.3 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 383.4 GB | ≈ 403.6 | ✕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 14 × 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
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 150.1
#59 of 118 listed models · pre-0813 snapshot · CI 148.4–151.9
- LMArena Text 1,458
#42 of 163 listed models · CI 1,454–1,462 · 56,904 votes
- Epoch AI · Chess Puzzles 19%
#67 of 85 listed models · pre-0813 snapshot, max effort · ±3.94
Also listed: high effort 16% · reasoning off 4%
- Epoch AI · FrontierMath Tier 4 v2 2.4%
#59 of 65 listed models · pre-0813 snapshot, max effort · ±2.44
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 7 – Nov 5, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Nov 8, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 24 – 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 |
|---|---|---|
| Humanity's Last Exam | no tools, text-only subset, max reasoning effort | 42.7% |
| with tools, max reasoning effort | 60% | |
| Terminal-Bench 2.1 | DeepSeek Harness minimal mode, max reasoning effort | 87.9% |
| GPQA Diamond | pass@1, max reasoning effort | 92.4% |
Included in coding plans
News
All news →- 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 →- Now priced on Alibaba Cloud Model Studio, China Input ¥12.00 · Output ¥24.00
- Now priced on Alibaba Cloud Model Studio, China Input ¥12.00 · Output ¥24.00
- 1 new price on Alibaba Cloud Model Studio, International Cache read $0.20
- 4 new prices on Volcengine Ark, cn-beijing Cache read (Flex tier) ¥0.30 · Input (Batch) ¥4.50 · Cache read (Batch) ¥0.30 · Output (Batch) ¥13.50
- 6 new prices on DeepSeek API Cache read (Off-peak hours) $0.022 · Cache read (Peak hours) $0.044 · Input (Off-peak hours) $0.66 · Input (Peak hours) $1.32 · +2 more
Sources
- deepseek-ai/DeepSeek-V4-Pro-0813 model card (opens in a new tab) huggingface.co · checked Nov 9, 2026
- 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
- 硅基流动：模型价格in Chinese (opens in a new tab) siliconflow.cn · checked Nov 8, 2026
- 火山方舟：模型价格in Chinese (opens in a new tab) docs.volcengine.com · checked Nov 9, 2026
- DeepSeek API change log (opens in a new tab) api-docs.deepseek.com · checked Nov 9, 2026
- DeepSeek-V4-Pro model card (deepseek-ai on Hugging Face) (opens in a new tab) huggingface.co · checked Nov 9, 2026
- models.dev: deepseek/deepseek-v4-pro (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- DeepSeek V4 Pro model (opens in a new tab) alibabacloud.com · checked Nov 9, 2026
- Text generation models - Qwen, DeepSeek, GLM | Model Studio - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Nov 1, 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 11, 2026
- Chat Completions API | DeepSeek API Docs (opens in a new tab) api-docs.deepseek.com · checked Nov 9, 2026
- deepseek-ai/DeepSeek-V4-Pro · Hugging Face (opens in a new tab) huggingface.co · checked Nov 7, 2026
- DeepSeek-V4-Pro 正式版上线 | DeepSeek API Docsin Chinese (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-Pro model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- deepseek-ai/DeepSeek-V4-Pro model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- deepseek-ai/DeepSeek-V4-Pro config.json (opens in a new tab) huggingface.co · checked Nov 9, 2026
- deepseek-ai/DeepSeek-V4-Pro files (opens in a new tab) huggingface.co · checked Nov 7, 2026
- deepseek-ai/DeepSeek-V4-Pro README.md (opens in a new tab) huggingface.co · checked Nov 7, 2026
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Nov 9, 2026
- DeepSeek (opens in a new tab) alibabacloud.com · checked Nov 8, 2026
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Nov 9, 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