Textby Xiaomi

MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

  • By price it is in the cheaper half of the 345 text models GenMagic runs (131st cheapest).
  • It scores 26.4 on the Artificial Analysis Intelligence Index, 51st of the 120 text models with a score.
  • It has scores on 25 public benchmarks, listed below with their sources.
  • It was listed on Apr 22, 2026.

Data last changed Nov 13, 2026 · tracked since Oct 29, 2026 · Every model change

Try MiMo-V2.5-Pro

Generate with MiMo-V2.5-Pro right here. Verify your email to start with free credits.

<$0.01
Try

Specifications

Context window

1M tokens

Max output

131K tokens

Input price

$0.65 / 1M tokens

Output price

$1.30 / 1M tokens

Cached input

$0.0054 / 1M tokens

Benchmarks

How MiMo-V2.5-Pro scores on public benchmarks. Each card links to the benchmark explainer and to the original source.

21.3

source date 2026-11-11
Source: openrouter

60.2

source date 2026-11-11
Source: openrouter

26.4

source date 2026-09-18
Source: openrouter
Design Arena: 3DDesign & Generation

1235 Elo

Source: designarena
Design Arena: CodeDesign & Generation

1262 Elo

Source: designarena
Design Arena: SVGDesign & Generation

1184 Elo

Source: designarena
DTBenchReasoning & Knowledge

84.5%

Source: epoch
GPQA DiamondReasoning & Knowledge

82.4%± 6.3

source date 2026-10-17
Source: openrouter
LMArena (Coding)Instruction & Preference

1501 Elo

source date 2026-11-11
Source: lmarena
LMArena: Creative WritingInstruction & Preference

1437 Elo

source date 2026-11-11
Source: lmarena
LMArena: Hard PromptsInstruction & Preference

1485 Elo

source date 2026-11-11
Source: lmarena

1481 Elo

source date 2026-11-11
Source: lmarena
LMArena: MathMathematics

1493 Elo

source date 2026-11-11
Source: lmarena
LMArena: Multi-TurnInstruction & Preference

1476 Elo

source date 2026-11-11
Source: lmarena
LMArena (Overall)Instruction & Preference

1464 Elo

source date 2026-11-11
Source: lmarena
LMCAReasoning & Knowledge

29.5

Source: epoch
ProofBenchMathematics

22%± 4.2

Source: epoch
tau-bench (Airline)Agentic & Tool Use

74%± 3.5

source date 2026-10-17
Source: openrouter
WebDev ArenaAgentic & Tool Use

1475 Elo

Source: epoch

Compare against every model in the full benchmark matrix.

Capabilities

Reasoning

Works through multi-step problems before answering, for harder tasks.

Tool use

Can call functions and tools, enabling agentic and structured workflows.

Structured output

Returns validated JSON that conforms to a schema you define.

Use MiMo-V2.5-Pro through the API

The model id is xiaomi/mimo-v2.5-pro. Requests bill your GenMagic balance at the price above, and each response reports what it cost.

curl
curl https://genmagic.co/api/v1/chat/completions \
  -H "Authorization: Bearer $GENMAGIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.5-pro",
    "messages": [{ "role": "user", "content": "Explain vector databases in two sentences." }]
  }'
Python (openai SDK)
from openai import OpenAI

client = OpenAI(base_url="https://genmagic.co/api/v1", api_key="YOUR_GENMAGIC_API_KEY")

resp = client.chat.completions.create(
    model="xiaomi/mimo-v2.5-pro",
    messages=[{"role": "user", "content": "Explain vector databases in two sentences."}],
)
print(resp.choices[0].message.content)

From an AI agent, call generate_text with "model": "xiaomi/mimo-v2.5-pro" on the GenMagic MCP server. Keys, limits and every endpoint are in the API documentation.

Use MiMo-V2.5-Pro in n8n

  1. In n8n, open the nodes panel, search for GenMagic and install it (a verified community node), then add it to your workflow.
  2. Set Resource to Text and Operation to Generate.
  3. In Model Name or ID, pick Xiaomi: MiMo-V2.5-Pro, or enter xiaomi/mimo-v2.5-pro as an expression.
  4. Connect your GenMagic API key (get one free). Each run is billed at the price above, and the node returns what it cost.

Ready-to-import workflows that already use the node are on GenMagic for n8n.

Similar-priced text models from other providers

Other text models GenMagic runs at a comparable price, on the same balance and API key.

ModelProviderPriceContext
Xiaomi: MiMo-V2.5-Pro (this model)Xiaomi$0.65 in / $1.30 out per 1M tokens1M
Thinking Machines: Inkling 2 SmallThinkingmachines$0.45 in / $1.50 out per 1M tokens1M
Reflection: Beam 1.0 501B A23BReflection$0.45 in / $1.50 out per 1M tokens1M
Z.ai: GLM 4.5 AirZ.AI$0.30 in / $1.65 out per 1M tokens131K
Qwen: Qwen3 Coder 480B A35BQwen$0.45 in / $1.50 out per 1M tokens262K
DeepSeek: DeepSeek V3.1 TerminusDeepSeek$0.41 in / $1.50 out per 1M tokens164K

Compare MiMo-V2.5-Pro

More from Xiaomi

All 5 Xiaomi models

Price and listing history

Every change GenMagic has recorded for MiMo-V2.5-Pro since it began tracking the model on Oct 29, 2026. Prices are GenMagic's, the same the studio and the API charge.

DateChangeBeforeAfter
Nov 13, 2026Price down 9%$0.72 in / $2.70 out per 1M tokens$0.65 in / $1.30 out per 1M tokens
Nov 13, 2026Updated: max output--
Nov 10, 2026Updated: context window--
Nov 1, 2026Price up 36%$0.53 in / $1.98 out per 1M tokens$0.72 in / $2.70 out per 1M tokens

Where these figures come from

  • Price: GenMagic's own price, what the studio and the API charge, recomputed from the provider's price list every few minutes and recorded daily. How pricing works.
  • Specs and description: as Xiaomi publishes them (model card on Hugging Face), checked daily.
  • Benchmarks: 25 scores from Artificial Analysis and OpenRouter, Design Arena, Epoch AI, LMArena, re-read daily. Each score above links to its source.
  • Changes: the data on this page last changed on Nov 13, 2026, tracked since Oct 29, 2026. Every model's new listings, price changes and retirements are in the model changes log, and how every figure on GenMagic is sourced is on our sources page.

Generate with MiMo-V2.5-Pro today

One GenMagic plan unlocks MiMo-V2.5-Pro and every other model across text, image, audio, and video.