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.…
MiMo-V2.5-ProReleased 22 Apr 2026 (Apr 2026)Pricing
List prices at GMI Cloud, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.304 | $0.609 | |
| Cached input 99% off input | $0.00252 | 99% off input |
What it costs a month
At GMI Cloud list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$110
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$95.61
- Coding agent1,000 requests a day, 40K in / 2K out, cached$148
- Overnight batch20,000 requests a day, 4K in / 0.4K out$877
Where to run it
4 hosts serve MiMo V2.5 Pro. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
GMI CloudInference MiMo-V2.5-Pro | $0.304 / $0.609 | MiMo-V2.5-Pro | |
OpenCode GoCloud mimo-v2.5-pro | $0.435 / $0.87 +43% vs headline | mimo-v2.5-pro | |
Novita AIInference mimo-v2.5-pro | $0.522 / $1.04 +71% vs headline | mimo-v2.5-pro | |
DeepInfraInference MiMo-V2.5-Pro | $1.00 / $3.00 +294% vs headline | MiMo-V2.5-Pro |
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: MITRuns in about 2455.6 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
- 47% less
- 47% less
- 31% less
Open-weight picks
- 3% less
- 8% less
- 31% less
- 53% less
Model line
Newer and older versions, at each lab's own price.
- Sep 2026MiMo V2.6 ProLatest$0.435 / $0.87
- Apr 2026MiMo V2.5 ProThis page$0.304 / $0.609
- UndatedMiMo V2 Pro$1.10 / $3.30
Call it
Using GMI Cloud's API.
from litellm import completion
response = completion(
model="gmi/MiMo-V2.5-Pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does MiMo V2.5 Pro cost?
On GMI Cloud, MiMo V2.5 Pro costs $0.304 per million input tokens and $0.609 per million output tokens. Cached input costs $0.00252 per million tokens.
Which APIs offer MiMo V2.5 Pro?
MiMo V2.5 Pro runs on 4 APIs: GMI Cloud, OpenCode Go, Novita AI and DeepInfra.
What is MiMo V2.5 Pro's context window?
1.1M tokens, with up to 1M tokens in one reply.
Is MiMo V2.5 Pro being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of MiMo V2.5 Pro?
Yes. MiMo V2.6 Pro is the newest model in this line, released on 21 Sep 2026.
What are cheaper alternatives to MiMo V2.5 Pro?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (47% less), GPT-6 Luna on OpenAI (47% less) and Qwen3.5 397B A17B on AIHubMix (3% less). Savings are on a mix of 3 input tokens to 1 output token.
When was MiMo V2.5 Pro released?
Xiaomi released it on 22 Apr 2026.
What is MiMo V2.5 Pro's API model id?
Use MiMo-V2.5-Pro with GMI Cloud. Other hosts use their own ids: mimo-v2.5-pro on OpenCode Go, mimo-v2.5-pro on Novita AI.
Sources
Raw catalog entry for MiMo-V2.5-Pro on GMI Cloud
{
"cache_read_input_token_cost": 2.52e-9,
"input_cost_per_token": 3.045e-7,
"litellm_provider": "gmi",
"max_input_tokens": 1050000,
"mode": "chat",
"output_cost_per_token": 6.09e-7,
"source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts"
}