Xiaomi MiMo V2.6 Flash API in India

MiMo V2.6 Flash is the smaller, faster member of Xiaomi's V2.6 family, live on unoblox as xiaomimimo/mimo-v2.6-flash. It accepts text and image input, supports tools and reasoning, and bills in rupees.

What MiMo V2.6 Flash is

Xiaomi released the V2.6 family in September 2026 under the MIT licence. Flash is the smaller model of the pair, at roughly 310 billion total parameters. unoblox lists a context length of 1,048,576 tokens with text and image in and text out.

A million-token window at a modest price makes it attractive for jobs that would otherwise need chunking.

Where it fits

• High-volume assistants where response speed and cost per request matter.
• Document and screenshot Q&A over long inputs.
• Cheap agent steps for planning and tool routing before a stronger model handles the hard parts.

Choose Flash for volume and Pro for the toughest tasks. If you want to benchmark neighbours, try Qwen3.8 Flash and DeepSeek V4 Flash (0731) with the same prompts, since only your own evaluation settles which fits.

₹ pricing for MiMo V2.6 Flash

On unoblox, MiMo V2.6 Flash costs ₹13.48 per million input tokens and ₹26.96 per million output tokens. That displayed price is what you are billed per token; nothing is added on top. Cached input tokens are listed at ₹0.27 per million. The model's context length on unoblox is 1,048,576 tokens.

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
MiMo V2.6 Flash	₹13.48	₹26.96
MiMo V2.6 Pro	₹41.40	₹83.77
Qwen3.8 Flash	₹10.88	₹36.78
DeepSeek V4 Flash (0731)	₹5.78	₹17.33

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹377.44 on MiMo V2.6 Flash (₹269.60 for input plus ₹107.84 for output). Live rates are always on the model page, and each request is rounded up to the nearest paisa.

Calling MiMo V2.6 Flash from the unoblox endpoint

unoblox is OpenAI-compatible, so any OpenAI SDK works by changing the base URL and key.

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_UNOBLOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomimimo/mimo-v2.6-flash",
    "messages": [{"role": "user", "content": "Summarise this support ticket in two lines."}],
    "max_tokens": 512
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_UNOBLOX_API_KEY",
    base_url="https://api.unoblox.ai/v1",
)
resp = client.chat.completions.create(
    model="xiaomimimo/mimo-v2.6-flash",
    messages=[{"role": "user", "content": "Summarise this support ticket in two lines."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)

For image input, pass an image_url content part:

resp = client.chat.completions.create(
    model="xiaomimimo/mimo-v2.6-flash",
    messages=[{"role": "user", "content": [
        {"type": "text", "text": "What does this chart show?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}},
    ]}],
    max_tokens=512,
)

Get a key at https://unoblox.ai/sign-in and top up your wallet in rupees.

Notes on parameters, billing and data

Use max_tokens to limit output. Images go in as image_url parts. The model runs at an external provider and not in India, so there is no data-residency claim; unoblox provides rupee pricing, GST invoicing and one endpoint.

Frequently asked questions

Is MiMo V2.6 Flash available in India? Yes, as xiaomimimo/mimo-v2.6-flash on https://api.unoblox.ai/v1.

Can it read images? unoblox lists text and image input.

What is its context length? 1,048,576 tokens.

How is it billed? In rupees per million tokens, with a GST invoice.

What is the difference from MiMo V2.6 Pro? Pro is the larger flagship; Flash is smaller, faster and cheaper.

Is it open weight? Xiaomi released the V2.6 family under the MIT licence.

Get started in rupees → https://unoblox.ai/sign-in