impulse

MiMo V2.5

Open weights

MiMo-V2.5 is a native omnimodal model by Xiaomi.

API id MiMo-V2.5Released 22 Apr 2026 (Apr 2026)
Input / 1M
$0.119
at GMI Cloud
Output / 1M
$0.238
at GMI Cloud
Context window
1.1M
tokens
Max output
262K
tokens per reply
Hosts
5
5 listings
Released
Apr 2026
22 Apr 2026

Pricing

List prices at GMI Cloud, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.119$0.238
Cached input
98% off input
$0.00238

What it costs a month

At GMI Cloud list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$43.05
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$37.70
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$59.12
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$343
Use your own numbers

Where to run it

5 hosts serve MiMo V2.5. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
GMI CloudInference
MiMo-V2.5
$0.119 / $0.238
mimo-v2.5
$0.14 / $0.28
+18% vs headline
Novita AIInference
mimo-v2.5
$0.168 / $0.336
+41% vs headline
mimo-v2.5
$0.186 / $0.372
+56% vs headline
DeepInfraInference
MiMo-V2.5
$0.40 / $2.00
+438% 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
Text
Produces
Text
Open weights
License: MIT
Runs in about 745.8 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

No host sells it for less than GMI Cloud.

Smaller Xiaomi models

No cheaper Xiaomi model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using GMI Cloud's API.

Python
from litellm import completion

response = completion(
    model="gmi/MiMo-V2.5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does MiMo V2.5 cost?

On GMI Cloud, MiMo V2.5 costs $0.119 per million input tokens and $0.238 per million output tokens. Cached input costs $0.00238 per million tokens.

Which APIs offer MiMo V2.5?

MiMo V2.5 runs on 5 APIs: GMI Cloud, OpenCode Go, Novita AI, Kyma API and DeepInfra.

What is MiMo V2.5's context window?

1.1M tokens, with up to 262K tokens in one reply.

Is MiMo V2.5 being retired?

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

What are cheaper alternatives to MiMo V2.5?

Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash on Sail (4% less). Savings are on a mix of 3 input tokens to 1 output token.

When was MiMo V2.5 released?

Xiaomi released it on 22 Apr 2026.

What is MiMo V2.5's API model id?

Use MiMo-V2.5 with GMI Cloud. Other hosts use their own ids: mimo-v2.5 on OpenCode Go, mimo-v2.5 on Novita AI, mimo-v2.5 on Kyma API.

Sources

Raw catalog entry for MiMo-V2.5 on GMI Cloud
{
  "cache_read_input_token_cost": 2.38e-9,
  "input_cost_per_token": 1.19e-7,
  "litellm_provider": "gmi",
  "max_input_tokens": 1050000,
  "mode": "chat",
  "output_cost_per_token": 2.38e-7,
  "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts"
}