AI model comparison
DeepSeek V4 Pro 0423 vs MiMo-V2.5
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
DeepSeek
DeepSeek V4 Pro 0423
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.
- Input / 1M
- $0.21
- Output / 1M
- $0.42
- Context
- 1.05M
Xiaomi
MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi.
- Input / 1M
- $0.14
- Output / 1M
- $0.28
- Context
- 1.05M
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
MiMo-V2.5
1.5x cheaper for a typical chat
Higher intelligence score
DeepSeek V4 Pro 0423
30.4 vs 25.2 on Artificial Analysis
Larger context window
MiMo-V2.5
1.05M vs 1.05M tokens
Newer release
DeepSeek V4 Pro 0423
Released April 24, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
DeepSeek V4 Pro 042330.4Coding index
DeepSeek V4 Pro 042359.4Agentic index
DeepSeek V4 Pro 042326.3Pricing
DeepSeek V4 Pro 0423 vs MiMo-V2.5 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | DeepSeek V4 Pro 0423 | |
|---|---|---|
| Input tokensPer 1M tokens | $0.21 | $0.14 |
| Output tokensPer 1M tokens | $0.42 | $0.28 |
| 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 0423$0.63Coding task
30K in, 4K out
DeepSeek V4 Pro 0423$7.93$2.19 cachedLong document summary
150K in, 2K out
DeepSeek V4 Pro 0423$32.16$3.45 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 0423 | |
|---|---|---|
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 384K tokens | 131K tokens |
| Input types | Text | Audio, Image, Text, Video |
| Output types | Text | Text |
| Reasoning effort levels | Extra high, High | Not available |
| Default reasoning effort | High | Not available |
| Release date | April 24, 2026 | April 22, 2026 |
Features
Supported features
API features available for each model.
| Metric | DeepSeek V4 Pro 0423 | |
|---|---|---|
| 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 0423View full model details- DeepSeek V4 Pro 0423 vs DeepSeek V4.1 Flash
- DeepSeek V4 Pro 0423 vs MiMo-V2.6-Flash
- DeepSeek V4 Pro 0423 vs GPT-6 Luna
- DeepSeek V4 Pro 0423 vs DeepSeek V4 Flash 0731
- DeepSeek V4 Pro 0423 vs DeepSeek V4 Flash 0423
- DeepSeek V4 Pro 0423 vs Hy3
- DeepSeek V4 Pro 0423 vs MiniMax M3
- DeepSeek V4 Pro 0423 vs Solar Mini 4
- DeepSeek V4 Pro 0423 vs Solar Pro 4
- DeepSeek V4 Pro 0423 vs Qwen3.8 Flash
- DeepSeek V4 Pro 0423 vs DeepSeek V4 Flash Vision Exp
- DeepSeek V4 Pro 0423 vs DeepSeek V3.2
- DeepSeek V4 Pro 0423 vs Ling 3.0 Flash VL
- MiMo-V2.5 vs MiMo-V2.6-Flash
- MiMo-V2.5 vs DeepSeek V4 Flash 0423
- MiMo-V2.5 vs Hy3
- MiMo-V2.5 vs Muse Spark 1.3 Contributor
- MiMo-V2.5 vs Solar Mini 4
- MiMo-V2.5 vs Solar Pro 4
- MiMo-V2.5 vs DeepSeek V3.2
- MiMo-V2.5 vs MiMo-V2.5-Pro
- MiMo-V2.5 vs Ling 3.0 Flash
- MiMo-V2.5 vs Qwen3.7 Plus
- MiMo-V2.5 vs Ling 3.0 Flash VL
- MiMo-V2.5 vs Ling 3.0 Flash Fin
Our take
MiMo-V2.5 is 1.5x cheaper for a typical chat. DeepSeek V4 Pro 0423 scores higher on the Artificial Analysis Intelligence Index (30.4 vs 25.2). MiMo-V2.5 has the larger context window (1.05M vs 1.05M tokens). 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 0423 or MiMo-V2.5 cheaper?
MiMo-V2.5 is cheaper for a typical chat (2K input tokens and 500 output tokens). MiMo-V2.5 costs $0.14 per 1M input tokens and $0.28 per 1M output tokens, while DeepSeek V4 Pro 0423 costs $0.21 per 1M input tokens and $0.42 per 1M output tokens.
Which has a bigger context window, DeepSeek V4 Pro 0423 or MiMo-V2.5?
MiMo-V2.5 supports up to 1.05M tokens of context, compared with 1.05M for DeepSeek V4 Pro 0423.
Is DeepSeek V4 Pro 0423 smarter than MiMo-V2.5?
On the Artificial Analysis Intelligence Index, DeepSeek V4 Pro 0423 scores 30.4 and MiMo-V2.5 scores 25.2, putting DeepSeek V4 Pro 0423 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use DeepSeek V4 Pro 0423 and MiMo-V2.5 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V4 Pro 0423 and MiMo-V2.5 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to DeepSeek V4 Pro 0423 and MiMo-V2.5 at the same time. Compare the answers side by side and keep the best one.