DeepSeek-R1 vs DeepSeek V4 Pro 0813 vs Qwen3 235B-A22B
DeepSeek V4 Pro 0813 comes out ahead, 68 to 51 and 51 on our weighted score, and it is the cheaper option too.
DeepSeekDeepSeek-R1
51/100- ECI139.0
- Price$0.70 / $2.60
- Context128K
- Our pickDeepSeek
DeepSeek V4 Pro 0813
68/100- ECI155.4
- Price$0.66 / $1.98
- Context1M
Alibaba (Qwen)Qwen3 235B-A22B
51/100- ECI139.4
- Price$0.70 / $2.80
- Context131K
DeepSeek V4 Pro 0813 is our pick
DeepSeek V4 Pro 0813 is the better all-round choice, scoring 68/100 against Qwen3 235B-A22B (51) and DeepSeek-R1 (51). It leads on capability, price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityDeepSeek V4 Pro 0813Capabilities Index (ECI): DeepSeek V4 Pro 0813 155.4 · Qwen3 235B-A22B 139.4 · DeepSeek-R1 139.0
- Lowest priceDeepSeek V4 Pro 0813DeepSeek V4 Pro 0813 $0.99 · DeepSeek-R1 $1.18 · Qwen3 235B-A22B $1.23 per 1M tokens (3:1 blend)
- Longest contextDeepSeek V4 Pro 0813DeepSeek V4 Pro 0813 1,000,000 · Qwen3 235B-A22B 131,072 · DeepSeek-R1 128,000 tokens
- Widest inputsSame inputsDeepSeek-R1: Text · DeepSeek V4 Pro 0813: Text · Qwen3 235B-A22B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek-R1 | DeepSeek V4 Pro 0813 | Qwen3 235B-A22B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 64 | 85 | 65 |
| Price | 25% | 47 | 50 | 46 |
| Inputs & features | 15% | 35 | 45 | 35 |
| Context window | 10% | 24 | 60 | 24 |
| Overall | 100% | 51/100 | 68/100 | 51/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-R1DeepSeek | DeepSeek V4 Pro 0813DeepSeek | Qwen3 235B-A22BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 139.0 | 155.4 (best) | 139.4 |
| ECI rank | #104 of 148 | #26 of 148 (best) | #103 of 148 |
| GPQA DiamondGraduate-level science questions | 71.7% | 91.7% (best) | 70.7% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 64.6% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 53.3% | 98.6% (best) | — |
| SimpleQA VerifiedShort factual questions | — | 52.9% | — |
| Price per million tokens | |||
| Input | $0.70 | $0.66 (best) | $0.70 |
| Output | $2.60 | $1.98 (best) | $2.80 |
| Cached input | — | $0.022 | — |
| Blended (3:1) | $1.18 | $0.99 (best) | $1.23 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 11 providers | Official DeepSeek API | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 1,000,000 tokens (best) | 131,072 tokens |
| Max output | 32,768 tokens | 384,000 tokens (best) | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yeslow · high · max | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | OpenMIT | Open |
| API model ID | — | deepseek-v4-pro | qwen3-235b-a22b |
| API providers | 12 | 37 (best) | 7 |
| Released | Jan 20, 2025 | Aug 12, 2026 | Apr 28, 2025 |
| Knowledge cutoff | Jul 2024 | — | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek-R1$12.20
- DeepSeek V4 Pro 0813$10.56
- Qwen3 235B-A22B$12.60
Which should you choose?
Which is better: DeepSeek-R1, DeepSeek V4 Pro 0813 or Qwen3 235B-A22B?
DeepSeek V4 Pro 0813 is the better all-round choice, scoring 68/100 against Qwen3 235B-A22B (51) and DeepSeek-R1 (51). It leads on capability, price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-R1, DeepSeek V4 Pro 0813 or Qwen3 235B-A22B?
DeepSeek V4 Pro 0813 is cheaper at $0.66 input / $1.98 output per million tokens (official DeepSeek API price). DeepSeek-R1 costs $0.70 input / $2.60 output per million tokens (median across 11 API providers); Qwen3 235B-A22B costs $0.70 input / $2.80 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.99 per million tokens for DeepSeek V4 Pro 0813 versus $1.18 for DeepSeek-R1 (1.2× as much) and $1.23 for Qwen3 235B-A22B (1.2× as much).
Which scores higher on benchmarks?
DeepSeek V4 Pro 0813 scores higher on the Capabilities Index (ECI): DeepSeek V4 Pro 0813 155.4 (#26 of 148), Qwen3 235B-A22B 139.4 (#103 of 148) and DeepSeek-R1 139.0 (#104 of 148). Their confidence ranges do not overlap (153.7–157.6 vs 135.2–140.8), so the gap is a real one. On individual benchmarks: GPQA Diamond — DeepSeek V4 Pro 0813 91.7%, DeepSeek-R1 71.7%, Qwen3 235B-A22B 70.7%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-R1, DeepSeek V4 Pro 0813 and Qwen3 235B-A22B yet, so there is no like-for-like coding score. On overall capability, DeepSeek V4 Pro 0813 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
DeepSeek V4 Pro 0813 has the largest context window at 1,000,000 tokens, against 131,072 for Qwen3 235B-A22B and 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, DeepSeek V4 Pro 0813 up to 384,000, Qwen3 235B-A22B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-R1 accepts text; DeepSeek V4 Pro 0813 accepts text; Qwen3 235B-A22B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (MIT), so you can self-host them.
Which is newer?
DeepSeek V4 Pro 0813 is the newest, released Aug 12, 2026. Qwen3 235B-A22B came out Apr 28, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, Qwen3 235B-A22B Apr 2025.
How do you decide the winner?
Each model gets a 0–100 score on 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 Oct 4, 2026.
Related comparisons
- DeepSeek-R1 vs Gemini 2.5 FlashGoogle · ECI 140.8
- DeepSeek-R1 vs GPT-4.1 miniOpenAI · ECI 135.0
- DeepSeek-R1 vs Mistral Medium 3Mistral AI · ECI 134.1
- DeepSeek V4 Pro 0813 vs Gemini 3.6 FlashGoogle · ECI 154.3
- DeepSeek V4 Pro 0813 vs Muse Spark 1.2Meta · ECI 155.0
- DeepSeek V4 Pro 0813 vs GLM-5.3Z.ai (Zhipu) · ECI 155.8
