Multimodal model with native visual and audio understanding on a 1M context, designed to reason and act across modalities in agentic workflows.
XiaomiText Generation1M contextProprietary EndpointNewMultimodal model with native visual and audio understanding on a 1M context, designed to reason and act across modalities in agentic workflows.
mimo-v2-5POST /v1/chat/completionsPOST /v1/responsesPOST /v1/messagesLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
MiMo V2.5 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id mimo-v2-5. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mimo-v2-5",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="mimo-v2-5",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the MiMo V2.5 API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| enable_thinking | boolean | true | - | Enable extended thinking mode. Slower but improves reasoning-heavy tasks. |
| tool_web_search | boolean | false | - | Allow the model to perform web searches when needed. |
| web_search_force | boolean | false | - | Force the model to always run a web search before answering. |
| web_search_max_keyword | number | 3 | 1 to 5 | Max number of keywords the model can use across web searches. |
| web_search_limit | number | 5 | 1 to 10 | Max number of web searches the model can perform per request. |
| video_fps | number | 2 | 0.1 to 10 | Frames-per-second sampled from input video for analysis. |
| video_resolution | enum | default | default, max | Resolution at which input video is sampled (e.g. 360p, 480p, 720p). |
| temperature | number | 0.7 | 0 to 2 | Sampling temperature. 0 = deterministic, 2 = maximum randomness. |
| top_p | number | 0.9 | 0 to 1 | Nucleus sampling probability mass. Lower = more focused. |
| max_tokens | number | 4096 | 1 to 65536 | Maximum tokens in the response. |
| stop | string | - | - | Up to 4 strings where the model will stop generating further tokens. |
| disable_formatting | boolean | false | - | Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search was used). The raw upstream answer with plain [N]... |
Omnimodal input (text, image, video, audio) with text output. Web search ($0.015/call) is charged only when invoked. Cached input tokens are billed at a steep discount.
On EmpirioLabs, MiMo V2.5 is billed pay as you go: Input $0.70 per 1M prompt tokens; Output $1.40 per 1M generated tokens; Implicit cache read $0.014 per 1M cached input tokens. The live rate card on this page always matches what the API charges.
MiMo V2.5 supports a 1M-token context window with up to 128,000 output tokens per response.
Yes. MiMo V2.5 serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to mimo-v2-5.
Yes. The EmpirioLabs playground runs MiMo V2.5 in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
