DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

MiMo-V2.5 is a native omnimodal model developed by XiaomiMiMo, designed to process and understand text, image, video, and audio through a unified architecture rather than relying on “bolted-on” components for each modality.
Built on a 310-billion-parameter Sparse Mixture of Experts (MoE) architecture — with only 15 billion parameters activated during inference — MiMo-V2.5 offers a strong balance of high-tier reasoning and computational efficiency. With a 1-million-token context window and agentic capabilities, it is engineered for complex multimodal perception, long-context reasoning, and autonomous workflows.
MiMo-V2.5 represents a meaningful step forward from its predecessor, MiMo-V2-Flash. By utilizing native, dedicated encoders for diverse data types, the model achieves a level of cohesion not commonly seen in large-scale models.
Key Technical Features
Configuration Notice: Developers who downloaded the model prior to recent repository updates should re-pull the config.json and tokenizer_config.json files to ensure optimal performance and avoid degraded behavior.
MiMo-V2.5 demonstrates competitive performance against frontier closed-source models, particularly in coding, temporal video reasoning, and agentic decision-making.
The model’s use of Reinforcement Learning (RL) places it near the Pareto frontier for daily agentic tasks.
| Benchmark | Category | MiMo-V2.5 Score | Claude Opus 4.6 | Gemini 3.1 Pro |
|---|---|---|---|---|
| Coding (General) | Programming/Logic | 71.8 | 77.1 | 67.8 |
| Claw-Eval Text | General Agentic | 65.8 | 70.8 | 68.5 |
| Terminal-Bench 2.0 | CLI Operations | 56.1 | 57.3 | 54.2 |
MiMo-V2.5 shows sharp perception for temporal reasoning, matching or approaching industry leaders in video and image understanding.
| Benchmark | Modality | MiMo-V2.5 Score | Gemini 3 Pro | Kimi K2.6 |
|---|---|---|---|---|
| Image Understanding | Vision-Language | 81.0 | 81.4 | 80.4 |
| Video-MME | Video | 83.5 | 84.2 | — |
| MMMU-Pro | Multi-discipline | 88.5 | — | — |
| CharXiv RQ | Chart/Diagram | 77.9 | 81.0 | 79.4 |
The model supports up to 1,000,000 tokens, validated through benchmarks like Graphwalks for path-finding and retrieval. A learnable attention sink bias helps reasoning accuracy remain stable even at the 1M token limit.
MiMo-V2.5 is hosted on DeepInfra, providing high-performance, low-latency inference via an OpenAI-compatible API.
Retrieve your API key from your DeepInfra Dashboard and include it in your HTTP headers:
Authorization: Bearer <YOUR_DEEPINFRA_API_KEY>
Using cURL
curl -X POST https://api.deepinfra.com/v1/openai/chat/completions \
-H "Authorization: Bearer $DEEPINFRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "XiaomiMiMo/MiMo-V2.5",
"messages": [
{
"role": "user",
"content": "Explain the advantages of a hybrid attention architecture in 2 sentences."
}
]
}'Using Python
import os
import requests
url = "https://api.deepinfra.com/v1/openai/chat/completions"
api_key = os.getenv("DEEPINFRA_API_KEY")
payload = {
"model": "XiaomiMiMo/MiMo-V2.5",
"messages": [{"role": "user", "content": "Explain the advantages of a hybrid attention architecture."}]
}
response = requests.post(url, headers={"Authorization": f"Bearer {api_key}"}, json=payload)
print(response.json())Pricing is usage-based, calculated per 1 million tokens. DeepInfra offers two tiers to balance cost and priority. For a cross-provider breakdown, see our MiMo-V2.5 provider pricing and deployment guide.
| Tier | Input Price | Output Price | Cached Input Price |
|---|---|---|---|
| Standard | $0.40 | $2.00 | $0.08 |
| Priority (1.5×) | $0.60 | $3.00 | $0.12 |
XiaomiMiMo’s MiMo-V2.5 is a capable and versatile model for the next generation of AI applications. By combining a 1M token context window with native omnimodal understanding and an efficient MoE architecture, it gives developers frontier-model capabilities at a comparatively lower resource cost.
Whether you are building agentic workflows, analyzing hour-long videos, or processing large document sets, MiMo-V2.5 offers the performance and flexibility for professional-grade deployment.
Qwen3.5 2B via DeepInfra: Latency, Throughput & Cost<p>About Qwen3.5 2B (Reasoning) Qwen3.5 2B is a compact 2-billion parameter open-weights model released in March 2026 as part of Alibaba Cloud’s Qwen3.5 Small Model Series. It employs an Efficient Hybrid Architecture combining Gated Delta Networks (a form of linear attention) with sparse Mixture-of-Experts, delivering high-throughput inference with minimal latency overhead — a significant architectural […]</p>
Kimi K2.6 Model Overview: Architecture, Features & Capabilities<p>Kimi K2.6 is Moonshot AI’s latest flagship open-source model, released on April 20, 2026 under a Modified MIT license. It is a native multimodal agentic model built on a 1-trillion parameter Mixture-of-Experts (MoE) architecture, with 32 billion parameters activated per token. The model is designed for long-horizon coding, autonomous execution, and multi-agent orchestration, and is […]</p>
Qwen3 Coder 480B A35B API Benchmarks: Latency & Cost<p>About Qwen3 Coder 480B A35B Instruct Qwen3 Coder 480B A35B Instruct is a state-of-the-art large language model developed by the Qwen team at Alibaba Cloud, specifically designed for code generation and agentic coding tasks. It is a Mixture-of-Experts (MoE) model with 480 billion total parameters and 35 billion active parameters per inference, enabling high performance […]</p>
© 2026 DeepInfra. All rights reserved.