ZMIME
Comparison · 2 models · Updated Nov 18, 2026

DeepSeek-V3.1 vs DeepSeek V3.2

DeepSeek V3.2 comes out ahead, 63 to 59 on our weighted score, and it is the cheaper option too.

Price in rating: Included · Exclude price

  1. DeepSeek

    DeepSeek-V3.1

    Released Aug 21, 2025

    59/100
    • ECI140.8
    • Price$0.27 / $1.00
    • Context131K
  2. Our pick

    DeepSeek

    DeepSeek V3.2

    Released Dec 1, 2025

    63/100
    • ECI146.3
    • Price$0.28 / $0.42
    • Context128K
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

DeepSeek V3.2 is our pick

DeepSeek V3.2 is the better all-round choice, scoring 63/100 against DeepSeek-V3.1 (59). It leads on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityDeepSeek V3.2Capabilities Index (ECI): DeepSeek V3.2 146.3 · DeepSeek-V3.1 140.8
  • Lowest priceDeepSeek V3.2DeepSeek V3.2 $0.315 · DeepSeek-V3.1 $0.453 per 1M tokens (3:1 blend)
  • Longest contextDeepSeek-V3.1DeepSeek-V3.1 131,072 · DeepSeek V3.2 128,000 tokens
  • Widest inputsSame inputsDeepSeek-V3.1: Text · DeepSeek V3.2: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDeepSeek-V3.1DeepSeek V3.2
CapabilityCapabilities Index (ECI)50%6974
Price25%6371
Inputs & features15%3535
Context window10%3232
Overall100%59/10063/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

DeepSeek-V3.1 vs DeepSeek V3.2 specifications side by side
SpecificationDeepSeek-V3.1DeepSeekDeepSeek V3.2DeepSeek
Capability
Capabilities Index (ECI)140.8146.3 (best)
ECI rank#112 of 158#87 of 158 (best)
GPQA DiamondGraduate-level science questions—83.4%
OTIS Mock AIME 2024–2025Competition mathematics—87.8%
Price per million tokens
Input$0.27 (best)$0.28
Output$1.00$0.42 (best)
Cached input——
Blended (3:1)$0.453$0.315 (best)
Long-context rateSame rateSame rate
Price sourceMedian of 18 providersMedian of 30 providers
Limits
Context window131,072 tokens (best)128,000 tokens
Max output8,192 tokens64,000 tokens (best)
Inputs and features
TextYesYes
ImagesNoNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningYesYes
Tool callingYesYes
Structured outputNoNo
Availability
WeightsOpenMIT LicenseOpenMIT License
API model ID——
API providers1830 (best)
ReleasedAug 21, 2025Dec 1, 2025
Knowledge cutoff—Jul 2024
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • DeepSeek-V3.1$4.70
  • DeepSeek V3.2$3.64
04 — Questions

Which should you choose?

Which is better: DeepSeek-V3.1 or DeepSeek V3.2?

DeepSeek V3.2 is the better all-round choice, scoring 63/100 against DeepSeek-V3.1 (59). It leads on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, DeepSeek-V3.1 or DeepSeek V3.2?

DeepSeek V3.2 is cheaper at $0.28 input / $0.42 output per million tokens (median across 30 API providers). DeepSeek-V3.1 costs $0.27 input / $1.00 output per million tokens (median across 18 API providers). At a typical mix of three input tokens to one output token, that is $0.315 per million tokens for DeepSeek V3.2 versus $0.453 for DeepSeek-V3.1 (1.4× as much).

Which scores higher on benchmarks?

DeepSeek V3.2 scores higher on the Capabilities Index (ECI): DeepSeek V3.2 146.3 (#87 of 158) and DeepSeek-V3.1 140.8 (#112 of 158). Their confidence ranges do not overlap (144.8–147.8 vs 137.6–143.9), so the gap is a real one.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-V3.1 and DeepSeek V3.2 yet, so there is no like-for-like coding score. On overall capability, DeepSeek V3.2 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

DeepSeek-V3.1 has the largest context window at 131,072 tokens, against 128,000 for DeepSeek V3.2. Maximum output per response: DeepSeek-V3.1 up to 8,192, DeepSeek V3.2 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-V3.1 accepts text; DeepSeek V3.2 accepts text. They handle the same number of input types.

Are any of these open source?

Yes, both publish their weights (MIT License), so you can self-host them.

Which is newer?

DeepSeek V3.2 is the newest, released Dec 1, 2025. DeepSeek-V3.1 came out Aug 21, 2025. Knowledge cutoff: DeepSeek V3.2 Jul 2024.

How do you decide the winner?

This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.