LiquidAI: LFM2.5-2.6B vs Xiaomi: MiMo-V2.5-Pro
A side-by-side comparison of LiquidAI: LFM2.5-2.6B ($1.22 / 1M tokens) and Xiaomi: MiMo-V2.5-Pro ($1.07 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.
Specifications
| LiquidAI: LFM2.5-2.6B | Xiaomi: MiMo-V2.5-Pro | |
|---|---|---|
| Provider | LiquidAI | Xiaomi |
| Input | $1.22 / 1M tokens | $1.07 / 1M tokens |
| Output | $1.75 / 1M tokens | $2.13 / 1M tokens |
| Cache read | $0.14 / 1M tokens | $0.00980 / 1M tokens |
| Context window | 128,000 | 1,050,000 |
| Max output | 8,192 | 945,000 |
| Input | text | text |
| Output | text | text |
| Tool calling | ||
| Structured output | ||
| Reasoning control | ||
| Added | Aug 11, 2026 | Apr 22, 2026 |
Key differences
- Xiaomi: MiMo-V2.5-Pro is 13% cheaper on input tokens.
- LiquidAI: LFM2.5-2.6B is 18% cheaper on output tokens.
- Xiaomi: MiMo-V2.5-Pro reads 8.2× more context (1,050,000 tokens).
- A request with 1,000 input and 500 output tokens costs $0.00210 with LiquidAI: LFM2.5-2.6B and $0.00213 with Xiaomi: MiMo-V2.5-Pro.
Switch with one string
Both models use the same endpoint and request shape. Change the model value from "liquid/lfm-2.5-2.6b" to "xiaomi/mimo-v2.5-pro" and prompts, streaming and tools keep working.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "xiaomi/mimo-v2.5-pro",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
More comparisons
- DeepSeek: DeepSeek V4.1 Flash 1017 vs Elorian: Glimpse
- DeepSeek: DeepSeek V4.1 Flash 1017 vs MiniMax: MiniMax M3.1 Flash
- DeepSeek: DeepSeek V4.1 Flash 1017 vs MoonshotAI: Kimi K3.1 Pro
- DeepSeek: DeepSeek V4.1 Flash 1017 vs Reflection: Beam 1.0 501B A23B
- Elorian: Glimpse vs MiniMax: MiniMax M3.1 Flash
- Elorian: Glimpse vs MoonshotAI: Kimi K3.1 Pro
- Elorian: Glimpse vs Reflection: Beam 1.0 501B A23B
- MiniMax: MiniMax M3.1 Flash vs MoonshotAI: Kimi K3.1 Pro