Skip to main content
AI Choice Engine

Model comparison

DeepSeek V3.1 vs DeepSeek V4.1 Flash

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

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

DeepSeek

DeepSeek V3.1

Budget · Open weights

vs

DeepSeek

DeepSeek V4.1 Flash

Balanced · Open weights

AI model capability comparison
SpecificationDeepSeek V3.1DeepSeek V4.1 Flash
ProviderDeepSeekDeepSeek
TierBudgetBalanced
Context window128KWinner: 1M
Max outputNot verifiedUnverified384K
Input / 1M tokensWinner: $0.25$0.30
Output / 1M tokensWinner: $0.95$1.20
WeightsOpenOpen
Parameters671B total / 37B active (MoE)552B MoE (causal encoder-decoder; 8B active for input, 16B for output)
Reasoning levelslow, high, maxlow, high, max
Modalitiestexttext, image
LicenseMITMIT
API model idNot publishedUnverifieddeepseek-flash
ReleasedAugust 21, 2025September 10, 2026
Artificial Analysis Intelligence Index (2026-09-26)13.5Not verifiedUnverified
Artificial Analysis Intelligence Index [max] (2026-09-26)Not verifiedUnverified39.5
DeepSWE 1.1 [max] (2026-09-10)Not verifiedUnverified74.2
Terminal-Bench 2.1 [max] (2026-09-10)Not verifiedUnverified90.6
GPQA Diamond [max] (2026-09-10)Not verifiedUnverified90.9

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. 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.

  • 2026-09-26
    Artificial Analysis

    Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.

    Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check measuredAt.

  • 2026-09-10
    DeepSeek V4.1-Flash release notes (vendor)

    Agentic software engineering: pass@1 on real repo tasks with reported cost per completed task.

    Directly comparable

Pricing tiers

DeepSeek V3.1: No first-party API: DeepSeek moved the deepseek-chat alias to V3.1-Terminus on 2025-09-22 (the alias itself was retired on 2026-07-24). Third-party hosts listed ~$0.25/$0.95 per MTok (secondary, last checked 2026-08-29) — verify with your host.

DeepSeek V4.1 Flash: Official peak rates $0.30/$1.20 per MTok; off-peak $0.15/$0.60 (50% of peak). Cache hit $0.006 peak / $0.003 off-peak. Peak hours are weekdays 01:00–04:00 and 06:00–10:00 UTC. Open weights (MIT). The legacy deepseek-v4-flash and deepseek-v4-flash-vision-exp ids temporarily route here.

BudgetOpen weightsRecord checked September 26, 2026

DeepSeek V3.1

DeepSeek V3.1 is a legacy open-weight (MIT) 671B/37B MoE with a 128K context — superseded by V3.1-Terminus, V3.2 and then V4.

Best for

  • Cost-sensitive hosted agents
  • High-volume coding assist
  • Open-weight deployments

Watch out

Legacy: DeepSeek's own API stopped serving V3.1 when deepseek-chat moved to V3.1-Terminus on 2025-09-22; hosted rates differ by provider and self-hosting needs datacentre VRAM.

BalancedOpen weightsRecord checked September 26, 2026

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is DeepSeek's new default — an open-weight (MIT) multimodal MoE that DeepSeek says beats V4-Pro on performance, cost and speed.

Best for

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

Watch out

Vendor benchmark claims are far ahead of its independent Artificial Analysis score (39.5 on v4.3.2); peak/off-peak billing means the hour you run matters.

When the cheaper one wins

DeepSeek V3.1 is cheaper on output at $0.95 per million tokens against $1.20 for DeepSeek V4.1 Flash — about 1.3×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 4/5 core specs verified on both sides — Not published for at least one side: max output.
  • 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 days — Newest catalog check was 2 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.

Related comparisons

Diving deeper on one model? DeepSeek V3.1 · DeepSeek V4.1 Flash

Common questions

DeepSeek V3.1 vs DeepSeek V4.1 Flash

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

Is DeepSeek V3.1 or DeepSeek V4.1 Flash cheaper for input?
DeepSeek V3.1 is cheaper at $0.25 per million input tokens, against $0.30 for DeepSeek V4.1 Flash — roughly 1.2× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; DeepSeek V3.1 has tiered pricing: No first-party API: DeepSeek moved the deepseek-chat alias to V3.1-Terminus on 2025-09-22 (the alias itself was retired on 2026-07-24). Third-party hosts listed ~$0.25/$0.95 per MTok (secondary, last checked 2026-08-29) — verify with your host. DeepSeek V4.1 Flash has tiered pricing: Official peak rates $0.30/$1.20 per MTok; off-peak $0.15/$0.60 (50% of peak). Cache hit $0.006 peak / $0.003 off-peak. Peak hours are weekdays 01:00–04:00 and 06:00–10:00 UTC. Open weights (MIT). The legacy deepseek-v4-flash and deepseek-v4-flash-vision-exp ids temporarily route here.
Is DeepSeek V3.1 or DeepSeek V4.1 Flash cheaper for output?
DeepSeek V3.1 is cheaper at $0.95 per million output tokens, against $1.20 for DeepSeek V4.1 Flash — roughly 1.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; DeepSeek V3.1 has tiered pricing: No first-party API: DeepSeek moved the deepseek-chat alias to V3.1-Terminus on 2025-09-22 (the alias itself was retired on 2026-07-24). Third-party hosts listed ~$0.25/$0.95 per MTok (secondary, last checked 2026-08-29) — verify with your host. DeepSeek V4.1 Flash has tiered pricing: Official peak rates $0.30/$1.20 per MTok; off-peak $0.15/$0.60 (50% of peak). Cache hit $0.006 peak / $0.003 off-peak. Peak hours are weekdays 01:00–04:00 and 06:00–10:00 UTC. Open weights (MIT). The legacy deepseek-v4-flash and deepseek-v4-flash-vision-exp ids temporarily route here.
Which has the larger context window, DeepSeek V3.1 or DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash accepts 1M tokens against 128K for DeepSeek V3.1. This only matters if you routinely send very long documents or large codebases.
Do DeepSeek V3.1 and DeepSeek V4.1 Flash support the same reasoning levels?
Yes — both accept the same effort settings: "low", "high", "max". Higher effort costs more and takes longer, so start low and raise it only where output quality actually improves.
Should I use DeepSeek V3.1 or DeepSeek V4.1 Flash?
DeepSeek V3.1 is the budget tier and DeepSeek V4.1 Flash the balanced tier. The useful question is whether your hardest task actually fails on the cheaper one — most production volume such as classification, extraction and summarisation does not.

Next step

Choosing between them

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

  • Input price: DeepSeek V3.1 costs $0.25 per 1M tokens versus $0.30 for DeepSeek V4.1 Flash — a 1.2x difference at the headline tier.
  • Context: DeepSeek V4.1 Flash takes 1M against 128K for DeepSeek V3.1 — only decisive if your prompts approach the smaller window.
  • Positioning: DeepSeek V3.1 sits in the budget tier, DeepSeek V4.1 Flash in the balanced tier — most production volume (classification, extraction, summarisation) does not need the pricier tier.
Run the model pickerEstimate stack costAll model comparisons

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