impulse

MiMo V2 Pro

API id mimo-v2-pro
Input / 1M
$1.10
at AIHubMix
Output / 1M
$3.30
at AIHubMix
Context window
1M
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at AIHubMix, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.10$3.30
Cached input
80% off input
$0.22

What it costs a month

At AIHubMix list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$498
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$436
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$779
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$3,432
Use your own numbers

Where to run it

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

HostIn / out per 1M
AIHubMixGateway
mimo-v2-pro
$1.10 / $3.30

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
Text
Produces
Text
Features
Prompt cachingBuilt-in web search

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

No host sells it for less than AIHubMix.

Smaller Xiaomi models

No cheaper Xiaomi model keeps its key capabilities.

Other frontier labs

  • Grok 4.20 Multi Agent
    xAI · on xAI
    $1.25 / $2.50
    Has every key capability
    5% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    9% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    72% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    88% less

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    47% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    48% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    52% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    58% 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 ProThis page$1.10 / $3.30

Call it

Using AIHubMix's API.

Python
from litellm import completion

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

Quick answers

How much does MiMo V2 Pro cost?

On AIHubMix, MiMo V2 Pro costs $1.10 per million input tokens and $3.30 per million output tokens. Cached input costs $0.22 per million tokens.

Which APIs offer MiMo V2 Pro?

MiMo V2 Pro runs on 1 API: AIHubMix.

What is MiMo V2 Pro's context window?

1M tokens.

Is MiMo V2 Pro being retired?

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

Is there a newer version of MiMo V2 Pro?

Yes. MiMo V2.6 Pro is the newest model in this line, released on 21 Sep 2026.

What are cheaper alternatives to MiMo V2 Pro?

Models that cost less and keep most of what it can do: Grok 4.20 Multi Agent on xAI (5% less), Gemini 3.8 Flash on Google AI Studio (9% less) and Motif 3 on ai& (47% less). Savings are on a mix of 3 input tokens to 1 output token.

What is MiMo V2 Pro's API model id?

Use mimo-v2-pro with AIHubMix.

Sources

Raw catalog entry for mimo-v2-pro on AIHubMix
{
  "cache_read_input_token_cost": 2.2e-7,
  "input_cost_per_token": 0.0000011,
  "litellm_provider": "aihubmix",
  "max_input_tokens": 1000000,
  "mode": "chat",
  "output_cost_per_token": 0.0000033,
  "source": "https://aihubmix.com/api/v1/models",
  "supports_prompt_caching": true,
  "supports_web_search": true
}