Skip to main content
AI Choice EngineAI Choice Engine

Model comparison

DeepSeek R1 vs DeepSeek V4 Pro

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

Catalog record checked September 3, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

DeepSeek

DeepSeek R1

Balanced · Open weights

vs

DeepSeek

DeepSeek V4 Pro

Frontier · Open weights

AI model capability comparison
SpecificationDeepSeek R1DeepSeek V4 Pro
ProviderDeepSeekDeepSeek
TierBalancedFrontier
Context window128KWinner: 1M
Max output33KWinner: 384K
Input / 1M tokensWinner: $0.55$1.32
Output / 1M tokensWinner: $2.19$3.96
WeightsOpenOpen
Parameters671B total / 37B active (MoE)1.6T total / 49B active (MoE)
Reasoning levelslow, high, maxlow, high, max
Modalitiestexttext
LicenseMITMIT
API model iddeepseek-reasonerdeepseek-v4-pro
ReleasedJanuary 20, 2025April 24, 2026
Artificial Analysis Intelligence Index (2026-08-14)42Winner: 53
SWE-bench Verified (2026-04-24)Not verifiedUnverified80.6
GPQA Diamond (2026-04-24)Not verifiedUnverified90.1
Humanity's Last Exam (2026-04-24)Not verifiedUnverified48.2
MMLU-Pro (2026-04-24)Not verifiedUnverified87.5

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

  • 2026-08-14: Artificial AnalysisComposite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
  • 2026-04-24: DeepSeek V4 Pro HF model card (vendor, Think Max, exact match)Real GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.

Pricing tiers: DeepSeek R1: Launch pricing $0.55/$2.19 per MTok (cache hit $0.14). Third-party hosts list ~$0.70/$2.50. Verify which weights a host serves. · DeepSeek V4 Pro: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Open weights (MIT). 1.6T/49B active MoE.

BalancedOpen weightsRecord checked September 3, 2026

DeepSeek R1

DeepSeek R1 is the open-weight (MIT) reasoning model — o1-class quality, 128K context.

Best for

  • Harder reasoning on a budget
  • Open-weight deployments
  • Agentic coding

Watch out

The deepseek-reasoner alias has been remapped to newer models on first-party API; pin the host/checkpoint you cite.

FrontierOpen weightsRecord checked September 3, 2026

DeepSeek V4 Pro

DeepSeek V4 Pro is the open-weight (MIT) flagship with a 1M-token context at a fraction of frontier API cost.

Best for

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

Watch out

Self-hosting needs datacentre VRAM; hosted rates vary by provider. Price single-source — verify.

When the cheaper one wins

DeepSeek R1 is cheaper on output at $2.19 per million tokens against $3.96 for DeepSeek V4 Pro — about 1.8×. 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 sidesInput and output rates are verified for both models.
  • 5/5 core specs verified on both sidesAll core specifications verified for both models.
  • 1 shared named benchmark with differing scoresMeasured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 daysNewest catalog check was 8 days ago.
  • Both models carry source citationsEach 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 R1 vs DeepSeek V4 Pro

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

Is DeepSeek R1 or DeepSeek V4 Pro cheaper for input?

DeepSeek R1 is cheaper at $0.55 per million input tokens, against $1.32 for DeepSeek V4 Pro — roughly 2.4× 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 R1 has tiered pricing: Launch pricing $0.55/$2.19 per MTok (cache hit $0.14). Third-party hosts list ~$0.70/$2.50. Verify which weights a host serves. DeepSeek V4 Pro has tiered pricing: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Open weights (MIT). 1.6T/49B active MoE.

Is DeepSeek R1 or DeepSeek V4 Pro cheaper for output?

DeepSeek R1 is cheaper at $2.19 per million output tokens, against $3.96 for DeepSeek V4 Pro — roughly 1.8× 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 R1 has tiered pricing: Launch pricing $0.55/$2.19 per MTok (cache hit $0.14). Third-party hosts list ~$0.70/$2.50. Verify which weights a host serves. DeepSeek V4 Pro has tiered pricing: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Open weights (MIT). 1.6T/49B active MoE.

Which has the larger context window, DeepSeek R1 or DeepSeek V4 Pro?

DeepSeek V4 Pro accepts 1M tokens against 128K for DeepSeek R1. This only matters if you routinely send very long documents or large codebases.

Do DeepSeek R1 and DeepSeek V4 Pro 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 R1 or DeepSeek V4 Pro?

DeepSeek R1 is the balanced tier and DeepSeek V4 Pro the frontier 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 R1 costs $0.55 per 1M tokens versus $1.32 for DeepSeek V4 Pro — a 2.4x difference at the headline tier.
  • Context: DeepSeek V4 Pro takes 1M against 128K for DeepSeek R1 — only decisive if your prompts approach the smaller window.
  • Measured capability: DeepSeek V4 Pro leads Artificial Analysis Intelligence Index 53 to 42 (measured 2026-08-14).
  • Positioning: DeepSeek R1 sits in the balanced tier, DeepSeek V4 Pro in the frontier tier — most production volume (classification, extraction, summarisation) does not need the pricier tier.

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