Model comparison
DeepSeek V3.1 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 V3.1
Budget · Open weights
DeepSeek
DeepSeek V4 Pro
Frontier · Open weights
| Specification | DeepSeek V3.1 | DeepSeek V4 Pro |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Tier | Budget | Frontier |
| Context window | 128K | Winner: 1M |
| Max output | 128K | Winner: 384K |
| Input / 1M tokens | Winner: $0.25 | $1.32 |
| Output / 1M tokens | Winner: $0.95 | $3.96 |
| Weights | Open | Open |
| Parameters | 671B total / 37B active (MoE) | 1.6T total / 49B active (MoE) |
| Reasoning levels | low, high, max | low, high, max |
| Modalities | text | text |
| License | MIT | MIT |
| API model id | Not publishedUnverified | deepseek-v4-pro |
| Released | August 21, 2025 | April 24, 2026 |
| Artificial Analysis Intelligence Index (2026-08-14) | 44 | Winner: 53 |
| SWE-bench Verified (2026-04-24) | Not verifiedUnverified | 80.6 |
| GPQA Diamond (2026-04-24) | Not verifiedUnverified | 90.1 |
| Humanity's Last Exam (2026-04-24) | Not verifiedUnverified | 48.2 |
| MMLU-Pro (2026-04-24) | Not verifiedUnverified | 87.5 |
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 V3.1: Third-party hosted ~$0.25/$0.95 per MTok; first-party peak/off-peak rates vary — verify on api-docs.deepseek.com. · 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.
DeepSeek V3.1
DeepSeek V3.1 is the open-weight (MIT) general model — 671B/37B MoE, 128K context, strong reasoning at low cost.
Best for
- Cost-sensitive hosted agents
- High-volume coding assist
- Open-weight deployments
Watch out
Self-hosting needs datacentre VRAM; hosted rates differ by provider.
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 V3.1 is cheaper on output at $0.95 per million tokens against $3.96 for DeepSeek V4 Pro — about 4.2×. 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 pickerEvidence 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.
- 5/5 core specs verified on both sides — All core specifications verified for both models.
- 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
- Verified within the last 90 days — Newest catalog check was 8 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.
- DeepSeek V3.1: DeepSeek — V3.1 (accessed 2026-08-29)
- DeepSeek V3.1: CloudPrice — DeepSeek V3.1 (accessed 2026-08-29)
- DeepSeek V4 Pro: DeepSeek — V4 news (accessed 2026-08-29)
- DeepSeek V4 Pro: DeepSeek API pricing (accessed 2026-08-29)
Related comparisons
- Claude Fable 5.1 vs DeepSeek V4 Pro
- Claude Fable 5 vs DeepSeek V4 Pro
- Claude Haiku 4.5 vs DeepSeek V3.1
- Claude Mythos 5.1 vs DeepSeek V4 Pro
- Claude Opus 5 vs DeepSeek V4 Pro
- DeepSeek R1 vs DeepSeek V3.1
Diving deeper on one model? DeepSeek V3.1 · DeepSeek V4 Pro
Common questions
DeepSeek V3.1 vs DeepSeek V4 Pro
Answered from the verified figures on this page rather than general guidance.
Is DeepSeek V3.1 or DeepSeek V4 Pro cheaper for input?
DeepSeek V3.1 is cheaper at $0.25 per million input tokens, against $1.32 for DeepSeek V4 Pro — roughly 5.3× 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: Third-party hosted ~$0.25/$0.95 per MTok; first-party peak/off-peak rates vary — verify on api-docs.deepseek.com. 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 V3.1 or DeepSeek V4 Pro cheaper for output?
DeepSeek V3.1 is cheaper at $0.95 per million output tokens, against $3.96 for DeepSeek V4 Pro — roughly 4.2× 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: Third-party hosted ~$0.25/$0.95 per MTok; first-party peak/off-peak rates vary — verify on api-docs.deepseek.com. 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 V3.1 or DeepSeek V4 Pro?
DeepSeek V4 Pro 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 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 V3.1 or DeepSeek V4 Pro?
DeepSeek V3.1 is the budget 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 V3.1 costs $0.25 per 1M tokens versus $1.32 for DeepSeek V4 Pro — a 5.3x difference at the headline tier.
- Context: DeepSeek V4 Pro takes 1M against 128K for DeepSeek V3.1 — only decisive if your prompts approach the smaller window.
- Measured capability: DeepSeek V4 Pro leads Artificial Analysis Intelligence Index 53 to 44 (measured 2026-08-14).
- Positioning: DeepSeek V3.1 sits in the budget 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.