Source-backed model guide · updated July 22, 2026
DeepSeek V4 Pro is the larger model in the DeepSeek V4 Preview family announced on April 24, 2026. DeepSeek describes it as a 1.6-trillion-parameter mixture-of-experts model with 49 billion parameters activated for each token, a published one-million-token context, and non-thinking plus two reasoning-effort modes. V4 Flash is the smaller, faster, lower-cost sibling. This page separates those publisher facts from what this independent chat application actually exposes.
Both models are mixture-of-experts systems: the total parameter count describes the complete weight set, while activated parameters describe the smaller subset used for a token. Total parameters are therefore not a direct measure of request cost or speed. The table below transcribes fields from DeepSeek’s release, model card, and API pricing page; it does not estimate unpublished values.
| Specification | V4 Pro | V4 Flash |
|---|---|---|
| API model ID | deepseek-v4-pro | deepseek-v4-flash |
| Total parameters | 1.6 trillion | 284 billion |
| Activated parameters | 49 billion | 13 billion |
| Published context length | 1 million tokens | 1 million tokens |
| Published maximum output | 384K tokens | 384K tokens |
| Reasoning modes | Non-think, Think High, Think Max | Non-think, Think High, Think Max |
| API concurrency limit | 500 | 2,500 |
| Instruct-weight precision | FP4 experts + FP8 mixed | FP4 experts + FP8 mixed |
API limits and concurrency are live-service values and can change. Recheck the official table before designing a production integration.
The official model card describes a hybrid of Compressed Sparse Attention and Heavily Compressed Attention. The goal is to reduce long-context compute and key/value-cache demand instead of applying full dense attention uniformly across one million tokens.
Manifold-Constrained Hyper-Connections are presented as a change to residual signal propagation. Treat this as a model-architecture claim from the technical report, not as a feature exposed or controlled by this website.
DeepSeek reports that Pro at a 1M context uses 27% of the single-token inference FLOPs and 10% of the KV cache of V3.2. Those are publisher measurements under its setup; they are not a promise about your provider’s latency or memory use.
For a deeper explanation of parameter counts, attention, open weights, and evidence boundaries, use the DeepSeek V4 architecture guide.
V4 Pro and Flash publish three operating modes. They are not three different weight sets, and increasing reasoning effort is not automatically better for every prompt.
Use for routine extraction, rewriting, classification, and low-risk questions where fast direct output matters. Evaluate accuracy because the model spends less explicit compute on reasoning.
Use for coding, analysis, multi-step planning, and difficult questions when extra latency is acceptable. This is usually the sensible starting point for measuring reasoning quality.
Use for boundary testing and the hardest tasks. It can consume more output tokens and time. Compare total cost and failure rate, not only a single successful answer.
DeepSeek’s API bills input and output tokens separately. At the July 22, 2026 source check, V4 Pro listed $0.003625 per million cache-hit input tokens, $0.435 per million cache-miss input tokens, and $0.87 per million output tokens. Flash listed $0.0028, $0.14, and $0.28 respectively. A cache hit is cheaper, but you should not assume every repeated prompt qualifies; use provider usage records.
A Pro request with 100,000 cache-miss input tokens and 10,000 output tokens would use the published formula: 0.1 × $0.435 plus 0.01 × $0.87, or about $0.0522 before any other provider or application charges. This is an arithmetic example, not a quote for this website.
DeepSeek-V4.io has a separate balance system. Its Starter, Pro, and Scale packs are one-time application purchases, not the official DeepSeek API price list and not a model selector. See the pricing and cost guide for the exact free balance, pack quantities, and checkout boundary.
The values below come from the official DeepSeek V4 model card’s “comparison across modes” table. Each cell is High / Max. They compare V4 Flash and V4 Pro under the publisher’s evaluation setup; they are not independent tests and should not be combined with scores from a different benchmark version.
| Benchmark and metric | Flash High / Max | Pro High / Max |
|---|---|---|
| MMLU-Pro (EM) | 86.4 / 86.2 | 87.1 / 87.5 |
| GPQA Diamond (Pass@1) | 87.4 / 88.1 | 89.1 / 90.1 |
| LiveCodeBench (Pass@1) | 88.4 / 91.6 | 89.8 / 93.5 |
| SWE Verified (resolved) | 78.6 / 79.0 | 79.4 / 80.6 |
| MRCR 1M (MMR) | 76.9 / 78.7 | 83.3 / 83.5 |
Uses documented model IDs, provider billing, API keys, rate limits, OpenAI-format and Anthropic-format endpoints, and a live pricing table.
Read the API guideModel repositories contain exact revisions, files, precision, license, runtime guidance, and publisher evaluation data. Local deployment feasibility depends on the selected artifact.
Read the local deployment guideIs an independent application with its own account, chat, project, usage, and billing behavior. It does not imply publisher ownership or guarantee a selectable Pro runtime.
Compare product boundariesDeepSeek announced the V4 Preview family on April 24, 2026. Any page that labels DeepSeek V4 as a 2024 release is mixing it up with an earlier DeepSeek generation.
No. They are separate model IDs and weight sets. Pro is the larger mixture-of-experts model at 1.6T total and 49B activated parameters; Flash is 284B total and 13B activated. They share the published 1M context and API feature set, but their cost, concurrency, knowledge capacity, and difficult-task behavior differ.
Not currently. DeepSeek-V4.io uses a server-configured provider and model. The chat UI does not promise that a plan name selects V4 Pro, and the runtime model should be verified from deployment telemetry rather than inferred from branding.
No. Starter, Pro, and Scale are one-time balance packs for this application. They are not DeepSeek model subscriptions and do not unlock a model selector.
One million tokens is the publisher-listed model context. Your usable request size can be lower because of provider limits, application validation, tool payloads, response reservations, memory, latency, and cost. Test the exact route you plan to use.
No. The table on this page transcribes selected publisher-reported results from the official model card. It is useful for locating a claim, not for proving universal superiority. Reproduce tests with your own prompts, tools, settings, and review rubric.
DeepSeek links official Pro, Flash, Base, and DSpark repositories. The exact model card and revision determine license, precision, file size, runtime support, and deployment feasibility. The availability of weights does not make a 1.6T model practical on ordinary consumer hardware.
Use the dated DeepSeek release notice for the announcement, the official model card and technical report for architecture and evaluations, and the live API pricing table for current limits and prices. Do not copy a number from an undated comparison page.
Source snapshot checked July 22, 2026. Live API limits, aliases, pricing, model revisions, and product behavior can change after this date.
