DeepSeek V4 Pro 0423
8953°
<deepseek-v4-pro>
Apps that support ModelTrends tags let you run/install models by copying this code in your prompt with no setup. Look for our icon in apps that support it, like Prism (below).
Run this model
Offers / Ads
Easy Creator (Prism) Web
Unlimited · flat fee
Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.
PirateDiffusion Telegram
Unlimited · flat fee
Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.
Pro studio (SpyGlass) Web
Unlimited · flat fee
Best for power users. Full control over models, settings and workflows in a browser studio.
Discord bot (Vector)
Unlimited · flat fee
Best for communities. Add it to your own server and run any workflow from a channel.
Unified Editor Web
Unlimited · flat fee
One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.
OpenRouter Terminal / API
Pay per token
Chat with this model in the browser or call it from your code with one API key.
Local apps
Requires setup
Set up local programs if your computer has capable hardware.
ModelDuel Web
Pay per use
Generate the same prompt on up to 50 checkpoint/base models at a time.
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
How much VRAM do I actually need for local AI?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
DeepSeek | 1,048,576 token context | $0.96/M input, $1.91/M output. 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. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical
Captain's notes
Notes from 2026-10-13
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model from DeepSeek, with 49B parameters active per token and a one-million-token context window. Its hybrid attention system cuts long-context compute dramatically compared to its predecessor, making it practical for full-codebase analysis and multi-step agent workflows. Weights are open; if you can run it, you are not locked to an API.
Known for
- 1M-token context window with a hybrid attention system that keeps inference costs manageable
- Strong across coding, math, knowledge and agentic benchmarks at the open-weights tier
- Adjustable reasoning effort, up to xhigh for maximum thinking depth
- 1.6T total parameters, 49B activated — frontier scale without activating everything per token
- Open weights available on Hugging Face for self-hosted deployment
Watch out for
- 1.6T total parameters means serious hardware requirements to run locally; most users will hit the API.
- Output tokens cost twice the input rate — long reasoning chains add up faster than you might expect.
- The model card describes this as a preview release; treat it accordingly for production use.
Prompts to try
Full codebase audit
I'm pasting a large Python codebase below. Identify every function that modifies global state, flag any that do so without thread safety, and suggest a refactor for the three riskiest ones. Explain your reasoning for each risk ranking. [paste code]
Multi-step agent plan
You are planning an automated pipeline to monitor a public GitHub repository, summarise new pull requests daily, classify them by type (bug fix, feature, docs, refactor), and post a digest to a Slack channel. List every step, the tools or APIs needed, failure modes to handle, and the order of implementation.
Hard math proof
Prove that for any prime p greater than 3, p squared minus 1 is always divisible by 24. Show each step of the proof clearly, state any lemmas you use, and then verify the result with three concrete examples.
Compare with
- DeepSeek V4.1 FlashOpen-weights model1,048,576 token context · $0.04/M input, $0.68/M output
- DeepSeek V4 Flash 0731Open-weights model1,048,576 token context · $0.01/M input, $1.28/M output
- DeepSeek V4 Flash 0423Open-weights model1,048,576 token context · $0.09/M input, $0.18/M output
- DeepSeek V4 Pro 0813Open-weights model1,048,576 token context · $1.32/M input, $3.96/M output
More text models from deepseek
Questions people ask
- Are the weights open and can I run DeepSeek V4 Pro locally?
- Yes, the weights are published on Hugging Face under deepseek-ai/DeepSeek-V4-Pro. Running them locally is a serious hardware undertaking given 1.6T total parameters, so most people will use the API unless they have a large multi-GPU setup.
- What does DeepSeek V4 Pro cost and what is the context limit?
- Via API it is $0.44 per million input tokens and $0.87 per million output tokens, with a one-million-token context window.
- How does DeepSeek V4 Pro differ from DeepSeek V4 Flash?
- Both share the same hybrid attention architecture and one-million-token context, but Pro has 1.6T total parameters (49B activated) versus Flash's 284B total (13B activated). DeepSeek says Flash-Max can approach Pro-level reasoning with a larger thinking budget, but Pro holds the edge on pure knowledge tasks and the most complex agentic workflows.
Captain's verdictThe most capable open-weights model DeepSeek has shipped — if you can feed it enough context, it earns its place.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #32 Hottest Text / LLM model · #32 Hottest Text / LLM text model
Not this creator?
Get your own badge
DeepSeek V4 Pro 0423 Popularity Trend
Heat score since 24 Apr 2026
Heat score
8,953°
This week
▲
22.7%
8,925° then, 8,953° now
This month
▲
157%
8,827° then, 8,953° now
Past year
n/a
Wasn't released/tracked
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,654°
OpenRouter tokens
3,257,945,734,845 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 325,794 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).
+299°
Adoption rate
About 9,616 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,953°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.325,794 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+1,654°8,654°running total
- 3Add the adoption rate.About 9,616 downloads a day right now, measured between two readings, at a quarter of the weight.+299°8,953°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,953°
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
DeepSeek V4 Pro 0423 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153