impulse

MiMo V2.6 Pro

Open weights

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.

API id mimo-v2.6-proReleased 21 Sep 2026 (8 weeks ago)
Input / 1M
$0.435
at Xiaomi MiMo
Output / 1M
$0.87
at Xiaomi MiMo
Context window
1M
tokens
Max output
131K
tokens per reply
Hosts
6
6 listings
Released
8 weeks ago
21 Sep 2026

Pricing

List prices at Xiaomi MiMo, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.435$0.87
Cached input
99% off input
$0.0036

What it costs a month

At Xiaomi MiMo list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$157
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$137
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$212
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,253
Use your own numbers

Where to run it

6 hosts serve MiMo V2.6 Pro. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
mimo-v2.6-pro
$0.435 / $0.87
GMI CloudInference
MiMo-V2.6-Pro
$0.348 / $0.696
−20% vs headline
mimo-v2-6-pro
$0.435 / $0.87
mimo-v2.6-pro
$0.435 / $0.87
mimo-v2.6-pro
$0.435 / $0.87
mimo-v2.6-pro
$0.581 / $1.17
+34% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImagesAudioVideo
Produces
Text
Features
Audio inputPrompt cachingVideo input
Open weights
License: MIT
Runs in about 2458.1 GB of GPU memory

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • GMI Cloud
    MiMo-V2.6-Pro
    $0.348 / $0.696
    20% less

Smaller Xiaomi models

No cheaper Xiaomi model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    15% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    63% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    63% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    52% less

Open-weight picks

  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    3% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    11% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    36% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    67% less

Model line

Newer and older versions, at each lab's own price.

  1. Sep 2026MiMo V2.6 ProLatest$0.435 / $0.87
  2. Apr 2026MiMo V2.5 Pro$0.304 / $0.609
  3. UndatedMiMo V2 Pro$1.10 / $3.30

Call it

Using Xiaomi MiMo's API.

Python
from litellm import completion

response = completion(
    model="xiaomi_mimo/mimo-v2.6-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does MiMo V2.6 Pro cost?

On Xiaomi MiMo, MiMo V2.6 Pro costs $0.435 per million input tokens and $0.87 per million output tokens. Cached input costs $0.0036 per million tokens. The cheapest host is GMI Cloud, at $0.348 per million input tokens and $0.696 per million output tokens.

Which APIs offer MiMo V2.6 Pro?

MiMo V2.6 Pro runs on 6 APIs: Xiaomi MiMo, GMI Cloud, EmpirioLabs AI, OpenCode Go, StreamLake and Kyma API.

What is MiMo V2.6 Pro's context window?

1M tokens, with up to 131K tokens in one reply.

Is MiMo V2.6 Pro being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of MiMo V2.6 Pro?

No. MiMo V2.6 Pro is the newest model in its line.

What are cheaper alternatives to MiMo V2.6 Pro?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (15% less), Claude Haiku 5.5 on Anthropic (63% less) and DeepSeek Flash on DeepSeek (3% less). MiMo V2.6 Pro itself costs 20% less on GMI Cloud. Savings are on a mix of 3 input tokens to 1 output token.

When was MiMo V2.6 Pro released?

Xiaomi released it on 21 Sep 2026.

What is MiMo V2.6 Pro's API model id?

Use mimo-v2.6-pro with Xiaomi MiMo. Other hosts use their own ids: MiMo-V2.6-Pro on GMI Cloud, mimo-v2-6-pro on EmpirioLabs AI.

Sources

Raw catalog entry for mimo-v2.6-pro on Xiaomi MiMo
{
  "cache_read_input_token_cost": 3.6e-9,
  "input_cost_per_token": 4.35e-7,
  "litellm_provider": "xiaomi_mimo",
  "max_input_tokens": 1048576,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 8.7e-7,
  "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md",
  "supported_endpoints": [
    "/v1/chat/completions"
  ],
  "supports_audio_input": true,
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_video_input": true,
  "supports_vision": true
}