AI model comparison
DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash 0731
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
DeepSeek
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
- Input / 1M
- $0.66
- Output / 1M
- $1.98
- Context
- 1.05M
DeepSeek
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
- Input / 1M
- $0.00
- Output / 1M
- $1.28
- Context
- 1.05M
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
DeepSeek V4 Flash 0731
3.6x cheaper for a typical chat
Higher intelligence score
DeepSeek V4 Pro 0813
36 vs 34.3 on Artificial Analysis
Larger context window
Tie
1.05M vs 1.05M tokens
Newer release
DeepSeek V4 Pro 0813
Released August 12, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
DeepSeek V4 Pro 081336DeepSeek V4 Flash 073134.3Coding index
DeepSeek V4 Pro 081368.8DeepSeek V4 Flash 073169.1Agentic index
DeepSeek V4 Pro 081341.3DeepSeek V4 Flash 073141Pricing
DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash 0731 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | DeepSeek V4 Pro 0813 | DeepSeek V4 Flash 0731 |
|---|---|---|
| Input tokensPer 1M tokens | $0.66 | $0.00 |
| Output tokensPer 1M tokens | $1.98 | $1.28 |
| Cached input (read)Per 1M tokens | $0.02 | $0.00 |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
DeepSeek V4 Pro 0813$2.31DeepSeek V4 Flash 0731$0.65Coding task
30K in, 4K out
DeepSeek V4 Pro 0813$27.72$8.58 cachedDeepSeek V4 Flash 0731$5.26$5.26 cachedLong document summary
150K in, 2K out
DeepSeek V4 Pro 0813$102.96$7.26 cachedDeepSeek V4 Flash 0731$3.28$3.28 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | DeepSeek V4 Pro 0813 | DeepSeek V4 Flash 0731 |
|---|---|---|
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 393K tokens | 944K tokens |
| Input types | Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Max, High, Low | Max, High, Low |
| Default reasoning effort | High | High |
| Release date | August 12, 2026 | July 31, 2026 |
Features
Supported features
API features available for each model.
| Metric | DeepSeek V4 Pro 0813 | DeepSeek V4 Flash 0731 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
DeepSeek V4 Pro 0813View full model details- DeepSeek V4 Pro 0813 vs DeepSeek V4.1 Flash
- DeepSeek V4 Pro 0813 vs GLM 5.3 Flash
- DeepSeek V4 Pro 0813 vs MiMo-V2.6-Flash
- DeepSeek V4 Pro 0813 vs Hy4 preview
- DeepSeek V4 Pro 0813 vs GPT-6 Luna
- DeepSeek V4 Pro 0813 vs Step 5 Preview
- DeepSeek V4 Pro 0813 vs Gemini 3.8 Flash
- DeepSeek V4 Pro 0813 vs GPT-5.6 Luna
- DeepSeek V4 Pro 0813 vs GLM 5.2
- DeepSeek V4 Pro 0813 vs Muse Spark 1.2
- DeepSeek V4 Pro 0813 vs Qwen3.8 27B
- DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash Vision Exp
- DeepSeek V4 Pro 0813 vs Gemini 3.6 Flash
- DeepSeek V4 Pro 0813 vs Muse Spark 1.1
DeepSeek V4 Flash 0731View full model details- DeepSeek V4 Flash 0731 vs DeepSeek V4.1 Flash
- DeepSeek V4 Flash 0731 vs GLM 5.3 Flash
- DeepSeek V4 Flash 0731 vs MiMo-V2.6-Flash
- DeepSeek V4 Flash 0731 vs Hy4 preview
- DeepSeek V4 Flash 0731 vs GPT-6 Luna
- DeepSeek V4 Flash 0731 vs Claude Opus 5.5
- DeepSeek V4 Flash 0731 vs GLM 5.3
- DeepSeek V4 Flash 0731 vs DeepSeek V4 Flash 0423
- DeepSeek V4 Flash 0731 vs Step 5 Preview
- DeepSeek V4 Flash 0731 vs Gemini 3.8 Flash
- DeepSeek V4 Flash 0731 vs Hy3
- DeepSeek V4 Flash 0731 vs GPT-5.6 Luna
- DeepSeek V4 Flash 0731 vs GPT-6.1 Sol
- DeepSeek V4 Flash 0731 vs GLM 5.2
- DeepSeek V4 Flash 0731 vs Claude Sonnet 5.5
- DeepSeek V4 Flash 0731 vs MiniMax M3
- DeepSeek V4 Flash 0731 vs GPT-6 Astra
- DeepSeek V4 Flash 0731 vs Claude Opus 5
- DeepSeek V4 Flash 0731 vs Claude Fable 5.1
- DeepSeek V4 Flash 0731 vs DeepSeek V4 Pro 0423
- DeepSeek V4 Flash 0731 vs Solar Pro 4
- DeepSeek V4 Flash 0731 vs Claude Haiku 5.5
- DeepSeek V4 Flash 0731 vs Qwen3.8 27B
- DeepSeek V4 Flash 0731 vs GLM 5.3 FlashX
- DeepSeek V4 Flash 0731 vs DeepSeek V4 Flash Vision Exp
- DeepSeek V4 Flash 0731 vs Gemini 3.6 Flash
- DeepSeek V4 Flash 0731 vs Muse Spark 1.1
- DeepSeek V4 Flash 0731 vs Gemini 3.5 Flash
- DeepSeek V4 Flash 0731 vs GPT-5.6 Luna Pro
- DeepSeek V4 Flash 0731 vs Qwen3.7 Max
- DeepSeek V4 Flash 0731 vs GLM 5
Our take
DeepSeek V4 Flash 0731 is 3.6x cheaper for a typical chat. DeepSeek V4 Pro 0813 scores higher on the Artificial Analysis Intelligence Index (36 vs 34.3). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is DeepSeek V4 Pro 0813 or DeepSeek V4 Flash 0731 cheaper?
DeepSeek V4 Flash 0731 is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V4 Flash 0731 costs $0.00 per 1M input tokens and $1.28 per 1M output tokens, while DeepSeek V4 Pro 0813 costs $0.66 per 1M input tokens and $1.98 per 1M output tokens.
Which has a bigger context window, DeepSeek V4 Pro 0813 or DeepSeek V4 Flash 0731?
DeepSeek V4 Pro 0813 supports up to 1.05M tokens of context, compared with 1.05M for DeepSeek V4 Flash 0731.
Is DeepSeek V4 Pro 0813 smarter than DeepSeek V4 Flash 0731?
On the Artificial Analysis Intelligence Index, DeepSeek V4 Pro 0813 scores 36 and DeepSeek V4 Flash 0731 scores 34.3, putting DeepSeek V4 Pro 0813 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use DeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to DeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 at the same time. Compare the answers side by side and keep the best one.