Overview
DeepSeek-V4 is the April 24, 2026 Preview release of DeepSeek's flagship model family, launched simultaneously in two variants: V4-Pro (1.6 trillion total / 49 billion active parameters) and V4-Flash (284 billion total / 13 billion active). Both variants ship with a 1M-token context window as the default, a new Hybrid Attention Architecture combining token-wise compression with DeepSeek Sparse Attention (DSA), and open weights on Hugging Face under the MIT License. V4 succeeds DeepSeek-V3.2 as the mainline general-purpose model, with OpenAI ChatCompletions and Anthropic API wire compatibility that lets developers migrate existing client code with only a base-URL change. The release positions DeepSeek as a leading open-weight alternative for agentic coding and long-context workflows, with V4-Flash and V4-Pro priced well below GPT-5.5 and Claude Opus 4.7 standard API rates.
What's New
Two Variants Released Simultaneously
V4 ships as two distinct models rather than a single flagship:
- DeepSeek-V4-Pro: 1.6T total parameters with 49B activated per token. Targets the hardest reasoning, math, agentic coding, and research workloads where capability justifies the higher price.
- DeepSeek-V4-Flash: 284B total / 13B active parameters. Delivers reasoning that "closely approaches V4-Pro" per DeepSeek's release notes, runs significantly faster, and matches V4-Pro on simpler agentic tasks at roughly one-twelfth the API price.
Both variants share the same architecture, tokenizer, and 1M-token default context window. The choice between them is primarily about cost-per-task and latency rather than capability tier.
Hybrid Attention Architecture + DSA
V4 introduces a Hybrid Attention Architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA), building on the sparse-selection ideas from DeepSeek Sparse Attention in the V3.2 line. The architecture delivers:
- 1M token context as the default across official DeepSeek services, API, and open weights, without a separate long-context tier.
- Lower long-context compute and memory cost: in the 1M-token setting, V4-Pro uses 27% of V3.2's single-token inference FLOPs and 10% of its KV cache; V4-Flash uses 10% and 7%, respectively.
- Substantial efficiency gains in both training and inference on long-context scenarios, maintaining output quality of dense attention while running at fraction of compute cost.
Benchmark Performance
DeepSeek positions V4-Pro as the first open-weight model to credibly compete with closed-source frontier models on the hardest evaluations:
- Math, STEM, and coding: V4-Pro-Max posts strong official results across published benchmarks, including GPQA Diamond 90.1, LiveCodeBench 93.5, Terminal Bench 2.0 67.9, SWE Verified 80.6, and SWE Pro 55.4.
- Agentic Coding: Open-source state-of-the-art on agentic coding benchmarks per DeepSeek's release note. The official model card publishes head-to-head rows against GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, K2.6 Thinking, and GLM-5.1 Thinking.
- World Knowledge: DeepSeek says V4-Pro leads current open models and trails only Gemini 3.1 Pro among the frontier models shown in its comparison; Gemini 3.1 Pro itself is not an open-weight model.
- V4-Flash: "Closely approaches V4-Pro" on reasoning and matches V4-Pro on simple agent tasks, per DeepSeek's own internal evaluations.
Numeric scores are published on the official Hugging Face model card for MMLU-Pro, GPQA Diamond, LiveCodeBench, SWE Verified, SWE Pro, Terminal Bench 2.0, BrowseComp, and related benchmarks; the full tech report is expected to follow with deeper architectural detail.
Dual Modes + Agent Framework Integration
Both V4-Pro and V4-Flash support reasoning-mode controls. The model card lists three reasoning effort modes—Non-think, Think, and Think Max—while the API docs describe switching between non-thinking and thinking modes:
- Thinking mode — Explicit chain-of-thought reasoning for harder problems where accuracy matters more than latency.
- Non-Thinking mode — Direct answer generation for simpler tasks where latency matters more than extended reasoning.
Integration with leading agent frameworks including Claude Code and OpenClaw is supported natively — V4 is positioned as a low-cost drop-in for teams already running AI agent workflows on paid closed models.
Legacy Model Deprecation Schedule
DeepSeek's OpenAI-style legacy endpoints deepseek-chat and deepseek-reasoner are scheduled to retire on July 24, 2026, three months after the V4 Preview launch. Existing integrations should plan migration to deepseek-v4-flash or deepseek-v4-pro endpoints before that date. The V4 endpoints accept the same request format, so migration is typically a model-name change rather than a protocol rewrite.
Availability & Access
Launch Availability (Apr 24, 2026)
V4-Pro and V4-Flash rolled out simultaneously across three surfaces on April 24, 2026:
- chat.deepseek.com: Free access with Expert Mode (Thinking) and Instant Mode (Non-Thinking) both defaulting to V4.
- API (platform.deepseek.com): Pay-as-you-go pricing available day one, OpenAI ChatCompletions and Anthropic API formats both supported.
- Open Weights (Hugging Face):
deepseek-ai/DeepSeek-V4-Pro,deepseek-ai/DeepSeek-V4-Flash, and their base checkpoints are published under the MIT License, with local deployment instructions in DeepSeek's official inference repository.
A technical report PDF accompanies the release, detailing the Hybrid Attention Architecture and DSA design choices for research teams wanting to reproduce or audit the work.
Regional & Compliance Considerations
The DeepSeek-hosted API and web surface are subject to Chinese jurisdiction and the provider's stated retention policy. Teams with strict data-residency, geopolitical-risk, or regulated-data requirements should evaluate the self-hosted open-weight path, which removes provider-hosted-traffic questions entirely. The open weights are published under the MIT License, which broadly permits commercial use, modification, distribution, and self-hosting subject to the license terms.
Pricing & Plans
V4 uses a three-tier access model identical to prior DeepSeek generations: free web chat, pay-as-you-go API, and free open weights.
chat.deepseek.com (Web)
- Free web access — V4 is available at chat.deepseek.com via Expert Mode and Instant Mode. Specific usage limits and account requirements are at DeepSeek's discretion.
API — Pay As You Go
| Model | Input | Output | Context |
|---|---|---|---|
| deepseek-v4-flash | $0.14/M tokens | $0.28/M tokens | 1,000,000 |
| deepseek-v4-pro | $1.74/M tokens | $3.48/M tokens | 1,000,000 |
Both endpoints support OpenAI ChatCompletions and Anthropic message formats, and both support Thinking / Non-Thinking dual modes.
Comparison with closed-source flagships:
| Provider | Input / Output per 1M tokens |
|---|---|
| GPT-5.5 | $5.00 / $30.00 |
| Claude Opus 4.7 | $5.00 / $25.00 |
| DeepSeek V4-Pro | $1.74 / $3.48 |
| DeepSeek V4-Flash | $0.14 / $0.28 |
V4-Pro lands at roughly one-third the input price and one-ninth the output price of GPT-5.5. V4-Flash pricing is more than an order of magnitude below GPT-5.5 and Claude Opus 4.7 standard API rates, making it attractive for high-volume workloads where cost dominates the cost-quality tradeoff.
Open Weights (Self-Hosted)
- Free under the MIT License from Hugging Face.
- V4-Flash (284B / 13B active) is the more practical self-hosting choice; V4-Pro's 1.6T parameters require substantial GPU infrastructure.
- vLLM and SGLang supported out of the box; quantized community builds typically appear within days of release.
Best For
- Cost-sensitive developers and startups moving off GPT-5.5 or Claude Opus 4.7 for high-volume workloads where V4-Flash's 35× cost advantage compounds quickly.
- Agentic coding teams using Claude Code, OpenClaw, or similar harnesses who want an open-weight drop-in at one-third the token cost.
- Long-context and codebase-wide workflows (entire repos, multi-document analysis, extended research) that benefit from 1M context without premium tiering.
- Research, math, and STEM users where V4-Pro's published math, STEM, coding, and reasoning benchmark results indicate strong capability.
- Self-hosters and privacy-sensitive organizations needing frontier capability on air-gapped or on-premise infrastructure.
- Teams maintaining DeepSeek
deepseek-chatordeepseek-reasonerintegrations who need to migrate before the July 24, 2026 legacy retirement deadline.
FAQ
When should I use V4-Pro vs V4-Flash?
V4-Pro when the workload is hard enough that the extra capability justifies 12× higher API cost—research math, hardest agentic coding tasks, long-horizon planning where a wrong step wastes many tokens. V4-Flash for high-volume API calls, chat, simple agentic tasks, and workloads where cost and latency dominate. DeepSeek's own framing: Flash "closely approaches" Pro on reasoning and matches it on simple agentic tasks.
How does DeepSeek-V4 compare to GPT-5.5 on API pricing?
V4-Pro is roughly 1/3 the input price ($1.74 vs $5.00/M) and 1/9 the output price ($3.48 vs $30.00/M) of GPT-5.5. V4-Flash is 35× cheaper on input ($0.14 vs $5.00/M) and 100× cheaper on output ($0.28 vs $30.00/M). For high-volume workloads, the math strongly favors DeepSeek; for absolute frontier capability on specific benchmarks, GPT-5.5 may still lead.
Can I run V4-Pro or V4-Flash locally?
Yes—both instruct variants and base checkpoints are published on Hugging Face under the MIT License, with local deployment instructions in DeepSeek's official inference repository. V4-Flash (284B total / 13B active) is the practical self-hosting choice; V4-Pro's 1.6T parameters require substantial multi-node GPU infrastructure.
What's the API compatibility story?
Both V4 endpoints support OpenAI ChatCompletions and Anthropic API formats. Migration is typically a base-URL, API key, and model-name change rather than guaranteed wire-for-wire compatibility across every SDK. Both Thinking and Non-Thinking modes are covered.
When are the legacy deepseek-chat and deepseek-reasoner models retiring?
July 24, 2026—three months after the V4 Preview launch. Migration to deepseek-v4-flash or deepseek-v4-pro is typically a model-name change rather than a protocol rewrite, since both legacy and V4 endpoints use the same OpenAI/Anthropic-compatible request formats.
Does V4-Flash really match V4-Pro?
Per DeepSeek's own release note, V4-Flash's reasoning "closely approaches" V4-Pro, and the two perform "on par" on simple agent tasks. On harder reasoning (hardest math, complex multi-step agentic workflows), V4-Pro retains a meaningful edge—the gap is real but narrower than the 12× price differential might suggest, which is why Flash is attractive for most API workloads.
