Skip to main content
AI Choice Engine

Model comparison

DeepSeek V4.1 Flash vs DeepSeek V4 Flash

Two DeepSeek tiers compared on the figures that decide which one a workload actually needs.

DeepSeek V4.1 Flash: profile checked October 25, 2026DeepSeek V4 Flash: profile checked October 25, 2026Individual provider fields may changeEvidence confidence: Insufficient data — see receipts below

DeepSeek

DeepSeek V4.1 Flash

Balanced · Open weights

vs

DeepSeek

DeepSeek V4 Flash

Balanced · Open weights

AI model capability comparison
SpecificationDeepSeek V4.1 FlashDeepSeek V4 Flash
ProviderDeepSeekDeepSeek
TierBalancedBalanced
Context window1M1M
Max output384KNot verifiedUnverified
Input / 1M tokensNot verifiedUnverifiedNot verifiedUnverified
Output / 1M tokensNot verifiedUnverifiedNot verifiedUnverified
WeightsOpenOpen
Parameters552B MoE backbone + 196B Engram memory (causal encoder-decoder; 8B active prefill, 16B decode)284B total / 13B active (MoE)
Reasoning levelslow, high, maxlow, high, max
Modalitiestext, imagetext
LicenseMITMIT
API model idNot verifiedUnverifieddeepseek-v4-flash
ReleasedSeptember 10, 2026April 24, 2026
Artificial Analysis Intelligence Index [max] · source date DeepSeek V4.1 Flash: 2026-10-0139Not verifiedUnverified
GPQA Diamond [max] · source date DeepSeek V4.1 Flash: 2026-10-0290.9Not verifiedUnverified
GPQA Diamond · source date DeepSeek V4 Flash: 2026-04-24Not verifiedUnverified88.1
DeepSWE 1.1 [max] · source date DeepSeek V4.1 Flash: 2026-10-0274.2Not verifiedUnverified
Terminal-Bench 2.1 [max] · source date DeepSeek V4.1 Flash: 2026-10-0290.6Not verifiedUnverified
Terminal-Bench 3.0 [max] · source date DeepSeek V4.1 Flash: 2026-10-0230Not verifiedUnverified
Terminal-Bench 4.0 [max] · source date DeepSeek V4.1 Flash: 2026-10-0231.2Not verifiedUnverified
SWE-bench Verified · source date DeepSeek V4 Flash: 2026-04-24Not verifiedUnverified79
Humanity's Last Exam · source date DeepSeek V4 Flash: 2026-04-24Not verifiedUnverified45.1
MMLU-Pro · source date DeepSeek V4 Flash: 2026-04-24Not verifiedUnverified86.2

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Pricing tiers

DeepSeek V4.1 Flash: The original September checkpoint is no longer separately sold through the rolling first-party alias. Its MIT weights remain available for self-hosting; no current independent hosting tariff is verified here. Current rolling deepseek-flash pricing belongs to DeepSeek-V4.1-Flash-1017, not a new evaluation of these original weights.

DeepSeek V4 Flash: Retired 2026-09-10 — no longer sold as the original checkpoint. Historical checkpoint tariffs are not verified here. The legacy deepseek-v4-flash ID now routes to V4.1-Flash-1017 at $0.30/$1.20 peak or $0.15/$0.60 off-peak, with $0.006/$0.003 cache reads. MIT weights remain. The 384K current API output ceiling and vision support belong to the routed revision, not these original text-only weights.

BalancedOpen weightsRecord checked October 25, 2026

DeepSeek V4.1 Flash

The September 2026 MIT-licensed DeepSeek V4.1 Flash checkpoint, retained separately from the October 17 API and weight update.

Best for

  • Open-weight price-performance
  • High-volume hosted agents
  • Self-hosting with MIT weights

Watch out

Vendor task scores and the Artificial Analysis composite index measure different things. API low/high/max effort is separate from the checkpoint's 1–100 control; non-thinking API mode is also supported. Peak/off-peak billing follows time and Chinese public holidays. Responses and Anthropic-compatible APIs are supported; FIM is non-thinking only. Native prompt encoding maps low/high/max to 50/75/100 and defaults to high=75 in thinking mode; this does not establish the hosted API default. The native 552B backbone excludes 196B Engram conditional memory. Published minimal inference is a readable reference, not verified production serving; its uninitialized self-test is not real-model validation. The 384K output cap is a hosted API limit, not a confirmed native generation ceiling. This is the September checkpoint profile: hosted limits are historical reference values, while current rolling-API calls and prices belong to Flash-1017. No successor benchmark result is inherited.

BalancedOpen weightsRecord checked October 25, 2026

DeepSeek V4 Flash

DeepSeek V4 Flash was the efficient open-weight (MIT) sibling of V4 Pro — retired from DeepSeek's API on 2026-09-10 and replaced by V4.1-Flash.

Best for

  • Open-weight deployments
  • Cost-sensitive inference
  • High-volume serving

Watch out

The original V4 Flash API checkpoint retired September 10; its old ID is still accepted and now serves Flash-1017. Original MIT weights remain available for self-hosting. Original API low/high/max settings are historical controls, not evidence of a matching native hosted menu or successor performance.

When the cheaper one wins

One of these rows is missing a verified output price, so this page will not name a cheaper winner. Run the model picker against the actual job instead of guessing.

Run the model picker

Evidence confidence: Insufficient data

How strong and complete the evidence behind this comparison is — not a prediction of which model is better. Hard limitations apply: missing pricing; evidence too sparse.

  • Pricing incomplete — No verified token pricing for DeepSeek V4.1 Flash and DeepSeek V4 Flash.
  • 4/5 core specs verified on both sides — Not published for at least one side: max output.
  • No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
  • Verified within the last 90 days — Older of the two catalog checks was 24 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Common questions

DeepSeek V4.1 Flash vs DeepSeek V4 Flash

Answered from the verified figures on this page rather than general guidance.

Which has the larger context window, DeepSeek V4.1 Flash or DeepSeek V4 Flash?
Both accept about 1M tokens of context, so document length will not decide between them.
Do DeepSeek V4.1 Flash and DeepSeek V4 Flash support the same reasoning levels?
Both expose these named effort settings: "low", "high", "max". The same labels do not guarantee equal compute budgets or behavior across providers. Compare quality, latency and cost on your own tasks.
Should I use DeepSeek V4.1 Flash or DeepSeek V4 Flash?
Both are classified in our balanced tier; this editorial grouping does not imply equal capability. DeepSeek V4.1 Flash is a candidate for open-weight price-performance; DeepSeek V4 Flash is a candidate for open-weight deployments. Compare accuracy, tool reliability, latency and cost on representative tasks.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

These two models match on every verified catalog figure — the decision comes down to provider preference, availability, and workload fit rather than published numbers.

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.