# DeepSeek-V4-Flash

> DeepSeek's lightweight V4 tier: a 284B / 13B-active open-weight MoE with a 1M-token context, near-Pro reasoning, released April 2026 and retired on the DeepSeek API in September 2026 in favour of V4.1-Flash.

- Maker: DeepSeek
- Line: DeepSeek V4
- Canonical page: https://ai-tldr.dev/models/deepseek-v4-flash/
- Updated: 2026-09-25

## In short

DeepSeek-V4-Flash is the smaller, faster, and cheaper of the two models in DeepSeek's V4 series, released as a preview on 24 April 2026 alongside the larger DeepSeek-V4-Pro. It has a 1M-token context window. You can use it through DeepSeek Platform.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 1M (max output 384K) | [1] |
| Input price | $0.22 off-peak · $0.44 peak (cached $0.007 off-peak · $0.014 peak) | [2] |
| Output price | $0.66 off-peak · $1.32 peak | [2] |
| Licence | MIT · open weights | [1] |
| Released | 24 April 2026 | [3] |
| Parameters | 284B total · 13B active | [1] |

## Sources

1. [DeepSeek-V4-Flash model card (Hugging Face)](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)
2. [DeepSeek API pricing](https://api-docs.deepseek.com/quick_start/pricing)
3. [DeepSeek-V4.1-Flash release and V4-Flash retirement notice (2026-09-10)](https://api-docs.deepseek.com/news/news260910)

## Overview

DeepSeek-V4-Flash is the smaller, faster, and cheaper of the two models in DeepSeek's V4 series, released as a preview on 24 April 2026 alongside the larger DeepSeek-V4-Pro. It is a Mixture-of-Experts language model with 284 billion total parameters, of which 13 billion are activated per token, and it natively supports a one-million-token context window with up to 384K tokens of output.

Like the Pro tier, DeepSeek-V4-Flash uses a Hybrid Attention Architecture that combines Compressed Sparse Attention and Heavily Compressed Attention. DeepSeek reports that in the 1M-token setting it needs only about 27% of the single-token inference FLOPs and 10% of the KV cache of DeepSeek-V3.2, which is what makes such a long context affordable. The model was pre-trained on more than 32 trillion tokens, runs in mixed FP4/FP8 precision (FP4 for MoE experts), and exposes three reasoning-effort modes: Non-think, Think High, and Think Max. DeepSeek says Flash in its Max mode approaches the reasoning quality of V4-Pro when given a larger thinking budget.

All weights are published on Hugging Face under the MIT License, so DeepSeek-V4-Flash is free for commercial use, fine-tuning, and self-hosting via vLLM, SGLang, or quantized GGUF builds in Ollama and LM Studio. On the DeepSeek API the legacy deepseek-chat and deepseek-reasoner aliases were retired on 2026-07-24 after having routed to Flash's non-thinking and thinking modes, and DeepSeek positions Flash as its low-cost agentic and coding workhorse, priced at a third of the V4-Pro rate.

On 2026-07-31 the `deepseek-v4-flash` API entered official public beta on a re-post-trained checkpoint DeepSeek released as DeepSeek-V4-Flash-0731. The checkpoint keeps the same architecture and parameter count as the April preview but reports substantially stronger agent scores — Terminal-Bench 2.1 82.7, DSBench-FullStack 68.7, Cybergym 76.7, Toolathlon Verified 70.3, DeepSWE 54.4, and NL2Repo 54.2, tested with the DeepSeek Harness minimal mode at max effort. The official V4-Flash natively supports the Responses API format and is specifically adapted for OpenAI Codex; DeepSeek says the official release of V4-Pro will follow.

## Benchmarks

- MMLU-Pro (Max): 86.2% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash))
- GPQA Diamond (Max): 88.1% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash))
- HMMT 2026 Feb (Max): 94.8% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash))
- LiveCodeBench (Max): 91.6% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash))
- SWE Verified (Max): 79% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash))
- SimpleQA-Verified (Max): 34.1% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash))
- MRCR 1M (Max): 78.7% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash))
- Terminal-Bench 2.1 (V4-Flash-0731): 82.7% ([source](https://api-docs.deepseek.com/updates))
- NL2Repo (V4-Flash-0731): 54.2% ([source](https://api-docs.deepseek.com/updates))
- Cybergym (V4-Flash-0731): 76.7% ([source](https://api-docs.deepseek.com/updates))
- DeepSWE (V4-Flash-0731): 54.4% ([source](https://api-docs.deepseek.com/updates))
- Toolathlon Verified (V4-Flash-0731): 70.3% ([source](https://api-docs.deepseek.com/updates))
- DSBench-FullStack (V4-Flash-0731): 68.7% ([source](https://api-docs.deepseek.com/updates))

## Pricing

- Input: $0.22 off-peak · $0.44 peak / 1M tokens
- Cached input: $0.007 off-peak · $0.014 peak / 1M tokens
- Output: $0.66 off-peak · $1.32 peak / 1M tokens

Input prices are cache-miss. DeepSeek bills V4 by time of day from 16:00 UTC on 16 August 2026: peak is 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, all other hours are off-peak, and off-peak is half the peak rate. Before that change V4-Flash was a flat $0.14 cache-miss input / $0.0028 cache-hit input / $0.28 output per 1M tokens. These were V4-Flash's rates until its 10 September 2026 retirement; since then the legacy `deepseek-v4-flash` name is served by DeepSeek-V4.1-Flash and billed at the Flash price ($0.15–$0.30 cache-miss input, $0.003–$0.006 cache-hit input, $0.60–$1.20 output per 1M tokens, off-peak to peak).

Source: https://api-docs.deepseek.com/quick_start/pricing

## Strengths

- Open MIT-licensed weights, free for commercial use, fine-tuning, and local deployment via vLLM, SGLang, Ollama, or LM Studio
- Native one-million-token context with efficient hybrid attention (roughly 27% of V3.2's per-token FLOPs and 10% of its KV cache at 1M)
- Selectable reasoning effort (Non-think / Think High / Think Max) to trade latency for depth
- Low API pricing — $0.22 per 1M cache-miss input tokens and $0.66 per 1M output off-peak, a third of the V4-Pro rate, with aggressive cache-hit discounts
- Strong coding and reasoning scores for its size, approaching V4-Pro in the Max mode (LiveCodeBench 91.6, SWE Verified 79.0)

## Best for

- High-volume agentic and coding workflows where cost and latency matter more than absolute peak quality
- Long-document and large-codebase analysis that needs the full 1M-token window on a budget
- Self-hosted / on-prem deployment where open MIT weights and a smaller 13B-active footprint are required
- A drop-in replacement for the retiring deepseek-chat and deepseek-reasoner endpoints via its non-thinking and thinking modes

## How to access

- [DeepSeek Platform](https://api-docs.deepseek.com/) — model id `deepseek-v4-flash`

## DeepSeek V4 versions

- [DeepSeek-V4-Pro (0813, GA)](https://ai-tldr.dev/models/deepseek-v4-pro/) (13 August 2026): General availability of the 1.6T Pro tier, superseding its April preview.
- DeepSeek-V4-Flash (0731 official public beta) (31 July 2026): Re-post-trained checkpoint (V4-Flash-0731); same architecture/size as the April preview. — this page
- DeepSeek-V4-Flash (April preview) (24 April 2026): Original open-weight preview released alongside V4-Pro.

## FAQ

### Is DeepSeek-V4-Flash open source?

Yes. The weights are published on Hugging Face under the MIT License, one of the most permissive open licenses, so you can download, run, fine-tune, and use DeepSeek-V4-Flash commercially, including self-hosted and on-prem. It can be served with vLLM or SGLang, or run from quantized GGUF builds in Ollama and LM Studio.

### How is DeepSeek-V4-Flash different from DeepSeek-V4-Pro?

Both shipped on 24 April 2026 and share the same 1M-token context, hybrid attention design, and MIT license. Flash is the smaller, cheaper tier — 284B total / 13B active parameters versus Pro's 1.6T / 49B — so it responds faster and DeepSeek prices it at exactly a third of Pro's per-token rate ($0.22 vs $0.66 per 1M cache-miss input tokens off-peak). DeepSeek says Flash in its Max reasoning mode approaches Pro's quality given a larger thinking budget.

### What are the reasoning modes in DeepSeek-V4-Flash?

It offers three reasoning-effort settings: Non-think for fast direct answers, Think High for deliberate step-by-step analysis, and Think Max (V4-Flash-Max) for maximum reasoning depth. The retiring deepseek-chat and deepseek-reasoner API aliases now route to Flash's non-thinking and thinking modes.

### How much does the DeepSeek-V4-Flash API cost?

DeepSeek bills V4-Flash by time of day. Off-peak it is $0.22 per 1M cache-miss input tokens, $0.007 per 1M cache-hit input tokens and $0.66 per 1M output tokens; at peak (01:00–04:00 and 06:00–10:00 UTC) those double to $0.44, $0.014 and $1.32. This schedule replaced a flat $0.14 / $0.0028 / $0.28 tariff at 16:00 UTC on 16 August 2026. DeepSeek retired V4-Flash on 10 September 2026; the legacy `deepseek-v4-flash` name is still accepted but is served by DeepSeek-V4.1-Flash and billed at the Flash price.

### What is DeepSeek-V4-Flash-0731?

DeepSeek-V4-Flash-0731 is a re-post-trained checkpoint of DeepSeek-V4-Flash that took over the `deepseek-v4-flash` API alias on 2026-07-31, moving the model from preview to official public beta. DeepSeek's change log notes it keeps the same architecture and parameter count as the April preview and was only re-post-trained, reporting large agent-benchmark gains — Terminal-Bench 2.1 82.7, DSBench-FullStack 68.7, Cybergym 76.7, Toolathlon Verified 70.3, DeepSWE 54.4, and NL2Repo 54.2 — plus native Responses API support and a Codex integration. The API calling method is unchanged.

## Links

- [DeepSeek-V4-Flash model card (Hugging Face)](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)
- [DeepSeek-V4.1-Flash release and V4-Flash retirement notice (2026-09-10)](https://api-docs.deepseek.com/news/news260910)
- [DeepSeek-V4 Preview Release announcement](https://api-docs.deepseek.com/news/news260424)
- [DeepSeek API Change Log (V4-Flash-0731 official public beta, 2026-07-31)](https://api-docs.deepseek.com/updates)
- [DeepSeek Codex integration guide](https://api-docs.deepseek.com/quick_start/agent_integrations/codex)
- [DeepSeek API pricing](https://api-docs.deepseek.com/quick_start/pricing)
- [DeepSeek-V4 technical report (PDF)](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf)
- [DeepSeek API docs](https://api-docs.deepseek.com/)
- [DeepSeek homepage](https://www.deepseek.com/)
- [DeepSeek Chat](https://chat.deepseek.com/)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/deepseek-v4-flash/