MiMo-V2.5-Pro vs Qwen3.5 397B A17B
API pricing, context window and capabilities for MiMo-V2.5-Pro and Qwen3.5 397B A17B, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.
Verdict
computed from the published numbersMiMo-V2.5-Pro wins on coding, on intelligence and on context window.
Price
Tied
Coding
MiMo-V2.5-Pro
Intelligence
MiMo-V2.5-Pro
Context window
MiMo-V2.5-Pro
Key takeaways
who wins on what, from the published numbersMiMo-V2.5-Pro wins
- Cheaper output ($0.87 vs $2.34 /1M)
- Larger context window (1M vs 262K)
- Higher max output (131K vs 66K)
Qwen3.5 397B A17B wins
- Cheaper input ($0.43 vs $0.39 /1M)
- More serving providers (3 vs 5)
- Supports vision
Cheaper overall
MiMo-V2.5-Pro
$0.43 + $0.87 /1M
Larger context
MiMo-V2.5-Pro
1M
More providers
Qwen3.5 397B A17B
5 providers
Pricing & specs
cheapest serving route · per 1M tokens| MiMo-V2.5-Pro | Qwen3.5 397B A17B | |
|---|---|---|
| Input $/1M | $0.43 | $0.39 best |
| Output $/1M | $0.87 best | $2.34 |
| Context window | 1M best | 262K |
| Max output | 131K best | 66K |
| Serving providers | 3 | 5 best |
| Released | 2026-04-22 | 2026-02-16 |
Benchmarks
Artificial Analysis indices, side by side| MiMo-V2.5-Pro | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence | 42.9 best | 34.3 |
| Coding | 60.2 best | 48.2 |
| GPQA Diamond | 87% | 89% best |
| Output speed | 36 t/s | 90 t/s best |
| Latency (TTFT) | 4.36s | 2.27s best |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
MiMo-V2.5-Pro
via OpenRouter
$3.04
Qwen3.5 397B A17B
via OpenRouter
$4.29
Capabilities
feature support, side by side| Feature | MiMo-V2.5-Pro | Qwen3.5 397B A17B |
|---|---|---|
| Vision | — | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, MiMo-V2.5-Pro or Qwen3.5 397B A17B?
Qwen3.5 397B A17B is cheaper for input ($0.43 vs $0.39 per 1M tokens). MiMo-V2.5-Pro is cheaper for output ($0.87 vs $2.34 per 1M tokens).
What is the context window difference between MiMo-V2.5-Pro and Qwen3.5 397B A17B?
MiMo-V2.5-Pro has a 1M-token context window and Qwen3.5 397B A17B has 262K tokens, so MiMo-V2.5-Pro can take a larger prompt.
How do MiMo-V2.5-Pro and Qwen3.5 397B A17B compare on benchmarks?
On the tracked Artificial Analysis indices, MiMo-V2.5-Pro leads on coding, and MiMo-V2.5-Pro 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