DeepSeek-V4-Pro benchmarks, pricing and specs
DeepSeek-V4-Pro is a DeepSeek model released on August 13, 2026 that takes text input and produces text. It costs $1.32 per 1M input tokens and $3.96 per 1M output tokens and accepts up to 1,000,000 tokens of context. It scores 1465 Elo on Arena Text, #29 of 49 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $1.32
- Per 1M output tokens
- $3.96
- Context window
- 1M
- Arena Text
- 1465 Elo · #29/49
Data verified October 13, 2026 · Dataset 2026-10-13
Key facts
- Provider
- DeepSeek
- Model family
- DeepSeek-V4
- Release date
- August 13, 2026
- Status
- Current
- Access
- API and open weights
- API model id
- deepseek-v4-pro
- Context window
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Input
- text
- Output
- text
- Task families
- text
- Declared capabilities
- reasoning, coding, agentic coding
DeepSeek-V4-Pro pricing
It is the #21 cheapest of 47 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. DeepSeek's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1465 Elo | #29 of 49 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 91.7% | #19 of 40 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 64.6% | #26 of 40 | October 12, 2026 | Epoch AI · 2026-10-12 |
| SimpleQA Verified | 52.9% | #18 of 36 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- The 0813 GA release: DeepSeek reports 87.9 on Terminal Bench 2.1 and 62.7 on DeepSWE, up from 72.1 and 12.8 for the preview
- MIT-licensed weights, a 1M-token context and up to 384K output tokens
- Off-peak rates are half the listed price: $0.66 input and $1.98 output per 1M tokens
Cautions
- The recorded rates are peak-hour prices (01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays)
- No image input on the DeepSeek API, where the cheaper deepseek-flash has it
- DeepSeek had planned to retire it in September before extending service, so check its status before a long commitment
Best for
- Agentic coding and terminal tasks
- Long-context jobs that need very long outputs
Alternatives to DeepSeek-V4-Pro
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, same or higher score
GLM-5.3-Flash
- 89% cheaper per 1M input tokens, $0.15 vs $1.32
- 10 points higher on Arena Text, 1475 vs 1465
- From Z.ai
Mistral Large 4
- 3% more per 1M input tokens, $1.36 vs $1.32
- 36 points lower on Arena Text, 1429 vs 1465
- From Mistral AI
Grok 4.20
- 5% cheaper per 1M input tokens, $1.25 vs $1.32
- 7 points higher on Arena Text, 1472 vs 1465
- From xAI
Grok 4.3
- 5% cheaper per 1M input tokens, $1.25 vs $1.32
- 23 points lower on Arena Text, 1442 vs 1465
- From xAI
Compare DeepSeek-V4-Pro with
- DeepSeek-V4-Pro vs Gemini 3.6 Flash
- DeepSeek-V4-Pro vs GLM-5.3
- DeepSeek-V4-Pro vs GLM-5.3-Flash
- DeepSeek-V4-Pro vs Grok 4.20
- DeepSeek-V4-Pro vs Grok 4.3
- DeepSeek-V4-Pro vs Mistral Large 4
- DeepSeek-V4-Pro vs Muse Glimmer
- DeepSeek-V4-Pro vs Muse Spark 1.3
- DeepSeek-V4-Pro vs Nemotron 3.5 Lightning
- DeepSeek-V4-Pro vs Step 5 Preview
DeepSeek-V4-Pro FAQ
How much does DeepSeek-V4-Pro cost?
DeepSeek-V4-Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens at the standard tier. It is the #21 cheapest of 47 current text models priced per 1M input tokens. Source: DeepSeek, verified October 13, 2026.
What is the context window of DeepSeek-V4-Pro?
DeepSeek-V4-Pro accepts up to 1,000,000 tokens of context. It can return up to 384,000 tokens in one response. That ranks #25 of 57 current text models by context length.
How does DeepSeek-V4-Pro score on independent benchmarks?
DeepSeek-V4-Pro scores 1465 Elo on Arena Text, #29 of 49 current models (Arena, measured October 8, 2026), 91.7% on GPQA Diamond, #19 of 40 current models (Epoch AI, measured October 12, 2026) and 64.6% on FrontierMath Tiers 1-3 (v2), #26 of 40 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not DeepSeek's own launch figures.
Is DeepSeek-V4-Pro open source or API only?
DeepSeek-V4-Pro is available both through DeepSeek's API and as open weights you can run yourself.
What are the best alternatives to DeepSeek-V4-Pro?
The closest current alternatives by price and measured performance are GLM-5.3-Flash (89% cheaper per 1M input tokens, $0.15 vs $1.32), Mistral Large 4 (3% more per 1M input tokens, $1.36 vs $1.32), Grok 4.20 (5% cheaper per 1M input tokens, $1.25 vs $1.32) and Grok 4.3 (5% cheaper per 1M input tokens, $1.25 vs $1.32).
Sources
- DeepSeek-V4-Pro update (2026-08-13) · DeepSeek · official · verified October 13, 2026
- DeepSeek-V4-Pro-0813 model weights · DeepSeek · official · verified October 13, 2026
- DeepSeek API pricing · DeepSeek · official · verified October 13, 2026
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "DeepSeek-V4-Pro Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-13. https://vandatateam.com/ai-model-benchmarks/deepseek-v4-pro
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether DeepSeek-V4-Pro fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls