Overall score
LMSpeed rank: #22 / 81Updated: Jun 16, 2026Confidence: 2
Xiaomi MiMo-V2.5 is a native omnimodal sparse MoE model (310B total, 15B active) with unified text, image, video, and audio understanding, built on the MiMo-V2-Flash backbone with dedicated vision and audio encoders. It supports up to 1M tokens of context, strong agentic workflows, and open weights on Hugging Face.
Compare MiMo-V2.5 API pricing across 63 providers. Input prices range from $0.0001 to $547.50 per million input. Tokeness offers the lowest rate at $0.0001/M. 2 providers offer free API credits or a free tier.
| Provider | Model Variant | Audit | Input ($/M) | Output ($/M) | Speed (t/s) | First token |
|---|---|---|---|---|---|---|
PICO AI3% | mimo-v2.5 | — | $2.80 | $14.00 | 96.7 t/s+8% | 1.66 s-12% |
6i2 API0% | mimo-v2.5 | — | $0.500 | $1.00 | 92.9 t/s+4% | 5.34 s |
Tokeness99.9% | mimo-v2.5 | — | $0.0001-100% | $0.0001-100% | 86.1 t/s | 2.08 s |
6345ywz API99.8% | mimo-v2.5 | — | $0.055-61% | $0.274-2% | 65.8 t/s | 6.20 s |
PackyAPI100% | mimo-v2.5 | — | $0.143 | $0.286 | — | — |
柏拉图AI100% | mimo-v2.5 | — | $0.384 | $1.92 | — | — |
CatClaw API100% | mimo-v2.5 | — | $0.0050-96% | $0.0050-98% | — | — |
天絮 API100% | mimo-v2.5 | 10010063100 | $2.86 | $14.29 | — | — |
Cuz AI100% | mimo-v2.5 | — | $0.400 | $2.00 | — | — |
速创API99.9% | mimo-v2.5 | — | $1.00 | $2.00 | — | — |
RenRen API99.7% | mimo-v2.5 | — | $75.00 | $75.00 | — | — |
ChooseC API99.6% | mimo-v2.5 | — | $1.00 | $2.00 | — | — |
VSLLM99.4% | mimo-v2.5-free | — | Free | Free | — | — |
初叶🍂Furry API97.9% | mimo-v2.5 | — | $0.050-64% | $0.050-82% | — | — |
猫羽霖API74.8% | mimo-v2.5 | 70728088 | $5.00 | $25.00 | — | — |
Moyanjdc API100% | mimo-v2.5 | — | Free | Free | — | — |
CatClaw API100% | mimo-v2.5 | — | $0.0050-96% | $0.0050-98% | — | — |
| mimo-v2.5 | — | $1.02 | $2.04 | — | — | |
Zero API100% | mimo-v2.5 | — | $0.0096-93% | $0.019-93% | — | — |
| mimo-v2.5 | — | $0.140 | $0.280 | — | — |
Pricing data from provider public APIs
mimo-v2-5-pro
Xiaomi MiMo-V2.5-Pro is a large open-source language model in the MiMo series, offering advanced reasoning and general-purpose capabilities.
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Standard benchmark data may include BenchLM and other public sources.
