DeepSeekOpen SourceCodingReasoningMultimodal

DeepSeek V4

DeepSeek’s current V4 generation — V4.1-Flash (deepseek-flash) is the live multimodal Flash SKU; V4-Pro-0813 remains on deepseek-v4-pro after 2026-09-14.

DeepSeek’s V4 generation — live Flash is V4.1-Flash (API id deepseek-flash): Causal Encoder–Decoder MoE, 552B backbone (8B active prefill / 16B decode), native image+text, and 1M context. MIT weights on Hugging Face. Legacy deepseek-v4-flash and deepseek-v4-flash-vision-exp aliases temporarily route here. deepseek-v4-pro still serves V4-Pro-0813 after 2026-09-14 at unchanged Pro rates (DeepSeek withdrew the planned Flash reroute).

Why DeepSeek V4 matters

Pin deepseek-flash for new DeepSeek API work. V4.1-Flash (2026-09-10) is a new CED MoE with native image+text, MIT weights, and lower Flash list prices. Aliases deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route there. After 2026-09-14, deepseek-v4-pro still serves Pro-0813 at unchanged Pro rates (DeepSeek withdrew the planned Flash reroute). Keep V3/R1 as open-checkpoint and reasoning baselines, not as assumed live API IDs.

Vision · Tool calling · Thinking · Coding

Last reviewed: 14 September 2026

Official pricing →

When to choose DeepSeek V4

Decision guidance for architects—not a feature list.

Best for

  • Cost-efficient agentic coding
  • 1M-context document and repo work
  • Native multimodal agent loops at Flash rates
  • OpenAI-compatible / Codex-style backends
  • Open-weight self-host where license allows

Avoid if

  • You require US-only data residency or a published V4.1-Pro SKU (neither is offered on this alias)
  • You require US-only enterprise packaging and SLAs

Strengths

Qualitative snapshot for architects—not a public ranking.

  • Agentic coding / value★★★★★
  • 1M context★★★★★
  • Open weights + API★★★★★
  • Multimodal★★★★
  • Enterprise packaging★★☆☆☆

Ecosystem

Built by

  • DeepSeek

    V4.1-Flash is DeepSeek’s current hosted Flash generation (native multimodal, 1M context); Pro-0813 remains on deepseek-v4-pro after 2026-09-14 at unchanged Pro rates.

Competes with

  • GPT-5.6

    Open / low-cost alternative for agentic coding and general workloads.

  • Kimi K3

    Peer open frontier MoE for long-horizon coding and 1M-context work.

Works with

  • vLLM

    Common serving path for DeepSeek open weights.

  • Cursor

    V4 is used as a cost-efficient coding-model backend in agent IDEs.

Recommended for

  • DeepSeek Models

    How V4 API IDs relate to V3/R1 open checkpoints and routing.

Often paired with

  • DeepSeek V3

    V3 remains a widely deployed open checkpoint; prefer V4 IDs for new API work.

  • DeepSeek R1

    R1 for dedicated hard reasoning; V4 for general/agent API traffic.

How DeepSeek V4 evolved

Key moments in chronological order.

  1. API

    V4 Pro API continues after planned Flash cutover

    DeepSeek keeps serving V4-Pro-0813 on deepseek-v4-pro after 2026-09-14 with billing unchanged, reversing the 2026-09-10 plan to route that alias to V4.1-Flash at Flash rates until V4.1-Pro.

  2. Model

    DeepSeek V4.1-Flash

    New CED MoE (552B backbone; 8B prefill / 16B decode) with native image+text and MIT weights. API id deepseek-flash. Aliases deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route here. The launch post also planned to route deepseek-v4-pro to Flash from 2026-09-14; DeepSeek later withdrew that cutover.

  3. Model

    V4-Flash-Vision-Exp multimodal API

    Experimental deepseek-v4-flash-vision-exp adds image+text input at Flash rates (up to 384 tokens/image). Matches Flash on text; multimodal agents improve vs text Flash. API-only; no open vision weights yet. Files API for free image reuse shipped the same day. Retired 2026-09-10: the alias now routes to V4.1-Flash.

  4. API

    V4 peak/off-peak API pricing live

    Peak/off-peak rates replace the prior flat V4 API prices from 16:00 UTC. Peak hours 01:00–04:00 and 06:00–10:00 UTC; off-peak is half of peak.

  5. Model

    V4-Pro-0813 generally available

    Pro leaves preview: agent upgrades, thinking effort low/high/max, native Responses API; peak/off-peak prices from 2026-08-16 16:00 UTC.

  6. Model

    V4-Flash-0731 agent upgrade

    Official Flash release with stronger agentic post-training; MIT weights on Hugging Face; same deepseek-v4-flash API ID.

  7. Deprecation

    Legacy chat/reasoner aliases retire

    deepseek-chat and deepseek-reasoner stop after Jul 24 2026 UTC; traffic moves to V4 Flash.

  8. Model

    DeepSeek V4 Preview

    V4-Pro (1.6T/49B) and V4-Flash (284B/13B) ship with 1M context and thinking modes.

  9. API

    deepseek-v4-pro / deepseek-v4-flash

    Official API IDs replace assuming historic chat/reasoner names map to V3/R1 weights.

Overview

DeepSeek’s V4 generation — live Flash is V4.1-Flash (API id deepseek-flash): Causal Encoder–Decoder MoE, 552B backbone (8B active prefill / 16B decode), native image+text, and 1M context. MIT weights on Hugging Face. Legacy deepseek-v4-flash and deepseek-v4-flash-vision-exp aliases temporarily route here. deepseek-v4-pro still serves V4-Pro-0813 after 2026-09-14 at unchanged Pro rates (DeepSeek withdrew the planned Flash reroute).

Capabilities

  • Vision: Yes
  • Audio: No
  • Tool calling: Yes
  • Thinking: Yes
  • MCP: No
  • Coding: Yes
  • Structured output: Yes

Technical specifications

Provider
DeepSeek
License
MIT (V4.1-Flash weights; verify other checkpoints)
Context window
1M
Parameters
V4.1-Flash MoE 552B backbone / 8B prefill / 16B decode (+196B Engram); Pro-0813 MoE 1.6T/49B on deepseek-v4-pro
Architecture
Causal Encoder–Decoder MoE (CSA2); V4-Pro-0813 remains DSA-class on deepseek-v4-pro
Release
2026-09
Modalities
Text, Image
Vision
Yes
Audio
No
Tool calling
Yes
Thinking
Yes
MCP
No
Open weights
Yes
API
Yes
Pricing (input)
Flash peak cache-miss $0.30 / cache-hit $0.006 per 1M (off-peak ½); Pro-0813 peak cache-miss $1.32
Pricing (output)
Flash peak $1.20 per 1M (off-peak ½); Pro-0813 peak $3.96

Supported modalities

Text · Image

Context window

1M (1,000,000 tokens)

Pricing

Input: Flash peak cache-miss $0.30 / cache-hit $0.006 per 1M (off-peak ½); Pro-0813 peak cache-miss $1.32
Output: Flash peak $1.20 per 1M (off-peak ½); Pro-0813 peak $3.96

Flash list prices from 04:00 UTC 2026-09-10. Peak hours 01:00–04:00 and 06:00–10:00 UTC weekdays; off-peak is half of peak. After 2026-09-14, deepseek-v4-pro still serves Pro-0813 at unchanged Pro rates. Verify live rates.

Availability

API: Yes
Chat UI: Yes
Open weights: Yes

Pin deepseek-flash for V4.1-Flash. Aliases deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route to V4.1-Flash. deepseek-v4-pro still serves Pro-0813 after 2026-09-14 (DeepSeek withdrew the planned Flash reroute). MIT weights: deepseek-ai/DeepSeek-V4.1-Flash. Serving engines may lag the weight drop — verify vLLM/SGLang before self-host.

Use cases

  • Cost-efficient agentic coding
  • 1M-context document and repo work
  • Native multimodal agent loops (screenshots / UI)
  • OpenAI-compatible / Codex-style agent backends
  • Self-hosted open-weight deployments (V4.1-Flash MIT weights)

Strengths

  • Native multimodal Flash with 1M context as the default hosted SKU
  • Much smaller KV cache vs V4-Flash (official: ~1/4 HBM, ~1/8 SSD)
  • Open MIT weights plus lower Flash API list prices from 2026-09-10
  • Legacy Flash / Vision-Exp aliases keep old clients working during the cutover

Limitations

  • V4.1-Pro is unpublished; Pro-0813 on deepseek-v4-pro continues until DeepSeek gives further notice
  • Self-host serving support may lag the Hugging Face drop — do not assume vLLM 0.29 serves V4.1-Flash
  • Enterprise packaging thinner than OpenAI/Anthropic

Related guides

Related benchmarks

Related research

Related GitHub

Related tools

Related rankings

Companies

Explore more models

All models →