AI Model Radar
中文 EN

DeepSeek V4 Flash

DeepSeek
Model overview

deepseek-v4-flash

DeepSeek's current public V4 Flash MoE model listed in the official catalog and released with open weights.

general LLMreasoningcodingagentlong contextchatcode generationsoftware engineering agententerprise accesslocal inference
External observationsCross-model riskCompareCompanyRankingsPublic signals
Model risk

Current observations

1current adverse observations
Negative / riskAPI / serviceAlias & lifecycleOfficial · Active

Legacy deepseek-chat and deepseek-reasoner aliases are deprecated after July 24

The current first-party API resolves legacy aliases to V4 Flash and publishes a deprecation date. Depending on generic aliases reduces version traceability and can break after the cutoff.

DeepSeek current API model documentationHigh confidenceObserved 2026-07-13Source checked 2026-07-15Current state verified 2026-07-15 Action

Move production calls to explicit V4 model IDs and record the served version.

Verify source
Representative version

deepseek-v4-flash

CompanyDeepSeek
Release2026-04-24
Release typeModel release
Parameters284B / 13B active
ArchitectureNot disclosed
Context1,000,000
Input modalitiestext
Output modalitiestext / code / tool_call
Tool use / function callingConfirmed: Tool use, Function calling
Structured output / reasoningConfirmed: Reasoning
Vision / audio / videoNot shown: Vision, Audio, Video
Open weights / LicenseWeights available / MIT
License sourcedeepseek-v4-flash-current · 2026-07-15
Vendor APIAvailable
deepseek-ai/DeepSeek-V4-Flash · Hugging Facedeepseek-v4-flash-current · 2026-04-24
OpenRouterOpenRouter listed
PricingOfficial · 2026-07-15: $0.14 / $0.28
OpenRouter · 2026-07-15: $0.098 / $0.196
input / output, per 1M tokens
BenchmarkNo reliable public source
Public signals1 activity snapshot
Use casesassistant chat / code generation / software engineering agent / enterprise API
Claim evidenceRelease eventdeepseek-ai/DeepSeek-V4-Flash · Hugging Facedeepseek-v4-flash · 2026-04-24
Model specs / weightsList Models | DeepSeek API DocsDeepSeek V4 Flash · deepseek-v4-flash
OpenRouter

Pricing / context / availability

OpenRouterOpenRouter listed
OpenRouter listingdeepseek/deepseek-v4-flash
Mapped versiondeepseek-v4-flash
deepseek-v4-flash-current
PricingOfficial · 2026-07-15: $0.14 / $0.28
OpenRouter · 2026-07-15: $0.098 / $0.196
input / output, per 1M tokens
Context1048576
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Public activity counters

Cumulative Hugging Face model-card downloads / likes / spaces

PlatformEntryDownloadsLikesSpacesTimeSource
huggingfacedeepseek-ai/DeepSeek-V4-Flash2,761,3591,7551002026-07-15T20:11:41.551ZView source
Evidence gaps

Public display boundary

No reliable benchmark sourceNo linkable real reviewSpeed/latency not disclosed