DeepSeek-V3 vs DeepSeek-V3.1
DeepSeek-V3.1 comes out ahead, 59 to 52 on our weighted score, and it is the cheaper option too.
Price in rating: Included · Exclude price
DeepSeek
DeepSeek-V3
52/100- ECI131.7
- Price$0.32 / $1.10
- Context131K
- Our pick
DeepSeek
DeepSeek-V3.1
59/100- ECI140.8
- Price$0.27 / $1.00
- Context131K
Add a model
Make it a three-way comparison.
DeepSeek-V3.1 is our pick
DeepSeek-V3.1 is the better all-round choice, scoring 59/100 against DeepSeek-V3 (52). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityDeepSeek-V3.1Capabilities Index (ECI): DeepSeek-V3.1 140.8 · DeepSeek-V3 131.7
- Lowest priceDeepSeek-V3.1DeepSeek-V3.1 $0.453 · DeepSeek-V3 $0.515 per 1M tokens (3:1 blend)
- Longest contextAbout the sameDeepSeek-V3 131,072 · DeepSeek-V3.1 131,072 tokens
- Widest inputsSame inputsDeepSeek-V3: Text · DeepSeek-V3.1: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek-V3 | DeepSeek-V3.1 |
|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 60 | 69 |
| Price | 25% | 61 | 63 |
| Inputs & features | 15% | 25 | 35 |
| Context window | 10% | 32 | 32 |
| Overall | 100% | 52/100 | 59/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | ||
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | 131.7 | 140.8 (best) |
| ECI rank | #136 of 158 | #112 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 56.5% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 15.8% | — |
| Price per million tokens | ||
| Input | $0.32 | $0.27 (best) |
| Output | $1.10 | $1.00 (best) |
| Cached input | — | — |
| Blended (3:1) | $0.515 | $0.453 (best) |
| Long-context rate | Same rate | Same rate |
| Price source | Median of 9 providers | Median of 18 providers |
| Limits | ||
| Context window | 131,072 tokens | 131,072 tokens |
| Max output | 8,192 tokens | 8,192 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | No | Yes |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | OpenDeepSeek Model License | OpenMIT License |
| API model ID | — | — |
| API providers | 9 | 18 (best) |
| Released | Dec 26, 2024 | Aug 21, 2025 |
| Knowledge cutoff | — | — |
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$5.40
DeepSeek-V3.1$4.70
Which should you choose?
Which is better: DeepSeek-V3 or DeepSeek-V3.1?
DeepSeek-V3.1 is the better all-round choice, scoring 59/100 against DeepSeek-V3 (52). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-V3 or DeepSeek-V3.1?
DeepSeek-V3.1 is cheaper at $0.27 input / $1.00 output per million tokens (median across 18 API providers). DeepSeek-V3 costs $0.32 input / $1.10 output per million tokens (median across 9 API providers). At a typical mix of three input tokens to one output token, that is $0.453 per million tokens for DeepSeek-V3.1 versus $0.515 for DeepSeek-V3 (1.1× as much).
Which scores higher on benchmarks?
DeepSeek-V3.1 scores higher on the Capabilities Index (ECI): DeepSeek-V3.1 140.8 (#112 of 158) and DeepSeek-V3 131.7 (#136 of 158). Their confidence ranges do not overlap (137.6–143.9 vs 129.1–134.0), so the gap is a real one.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3 and DeepSeek-V3.1 yet, so there is no like-for-like coding score. On overall capability, DeepSeek-V3.1 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 and DeepSeek-V3.1 share the same 131,072-token context window. Maximum output per response: DeepSeek-V3 up to 8,192, DeepSeek-V3.1 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-V3 accepts text; DeepSeek-V3.1 accepts text. They handle the same number of input types.
Are any of these open source?
Yes, both publish their weights (DeepSeek Model License and MIT License), so you can self-host them.
Which is newer?
DeepSeek-V3.1 is the newest, released Aug 21, 2025. DeepSeek-V3 came out Dec 26, 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.