DeepSeek V4 Pro 0423 vs MiMo-V2.5-Pro
API pricing, context window and capabilities for DeepSeek V4 Pro 0423 and MiMo-V2.5-Pro, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.
Verdict
computed from the published numbersDeepSeek V4 Pro 0423 wins on coding and on intelligence.
Price
Tied
Coding
DeepSeek V4 Pro 0423
Intelligence
DeepSeek V4 Pro 0423
Context window
Tied
Key takeaways
who wins on what, from the published numbersDeepSeek V4 Pro 0423 wins
- Higher max output (512K vs 131K)
- More serving providers (10 vs 3)
MiMo-V2.5-Pro wins
No clear edge on the tracked metrics.
Cheaper overall
Tied
Larger context
Tied
More providers
DeepSeek V4 Pro 0423
10 providers
Pricing & specs
cheapest serving route · per 1M tokens| DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | |
|---|---|---|
| Input $/1M | $0.43 | $0.43 |
| Output $/1M | $0.87 | $0.87 |
| Context window | 1M | 1M |
| Max output | 512K best | 131K |
| Serving providers | 10 best | 3 |
| Released | 2026-04-24 | 2026-04-22 |
Benchmarks
Artificial Analysis indices, side by side| DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | |
|---|---|---|
| Intelligence | 53.2 best | 42.9 |
| Coding | 68.8 best | 60.2 |
| GPQA Diamond | 93% best | 87% |
| Output speed | 68 t/s best | 36 t/s |
| Latency (TTFT) | 1.75s best | 4.36s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
DeepSeek V4 Pro 0423
via Tencent
$3.04
MiMo-V2.5-Pro
via OpenRouter
$3.04
Capabilities
feature support, side by side| Feature | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro |
|---|---|---|
| Vision | — | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro 0423 or MiMo-V2.5-Pro?
DeepSeek V4 Pro 0423 and MiMo-V2.5-Pro have the same cheapest published input and output rates.
What is the context window difference between DeepSeek V4 Pro 0423 and MiMo-V2.5-Pro?
Both DeepSeek V4 Pro 0423 and MiMo-V2.5-Pro have about a 1M-token context window.
How do DeepSeek V4 Pro 0423 and MiMo-V2.5-Pro compare on benchmarks?
On the tracked Artificial Analysis indices, DeepSeek V4 Pro 0423 leads on coding, and DeepSeek V4 Pro 0423 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI