DeepSeek · AI Model

DeepSeek V4 Flash

deepseek-v4-flash · Released date not recorded

Model profile

ProviderDeepSeek
FamilyDeepSeek V4
Modalitytext
Context1,000,000 tokens
Max output384,000 tokens
ReasoningYes
Tool callingYes
Structured outputYes
Open weightsNo / not recorded
Licence

Published Cybatar benchmarks

No verified Cybatar-run benchmark result has been published for this model yet.

Model economics

Pricing history

Versioned observations tied to the exact deployment and source date.

All model pricing →
EffectiveDeploymentModeInput / 1MCached / 1MOutput / 1MSource
23 Aug 2026DeepSeek standard USD 0.14USD 0.0028USD 0.28Source ↗
Lifecycle intelligence

Release & availability timeline

23 Aug 2026 · Pricing Change

DeepSeek V4 Flash pricing observation

Cached input represents cache-hit pricing; normal input is cache-miss pricing.

Evidence ↗
23 Aug 2026 · Model Availability

DeepSeek V4 API family current availability

DeepSeek lists V4 Flash and V4 Pro as current API models with 1M-token context support.

Evidence ↗
External research evidence

Published benchmark observations

Reported by independent evaluators or the model provider. These are contextual research observations, not Cybatar-run scores.

BenchmarkScoreConfiguration / harnessProvenanceSource
AA-Briefcase 2026-081285 EloModel evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
Artificial Analysis Intelligence Index v4.1.152 Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
GDPval-AA v21559 EloModel evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
Terminal-Bench 2.179 %Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
Tau3-Banking 1.0.131 %Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
SciCode 202650 %Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
Humanity's Last Exam 202637 %Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
GPQA Diamond 202691 %Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
AA-Omniscience Index 2026-08-16 Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis
AA-Omniscience Hallucination Rate 2026-0884 %Model evaluation · reasoning effort: max · release: 0731IndependentArtificial Analysis