MiMo V2.5

Model Deactivated

Xiaomi's full-modal perception model supporting native understanding of images, videos, audio, and text with 1M context. Agent performance comparable to MiMo V2.5 Pro.

mimo-v2.5
Context
1,048,576
tokens
Max output
131,072
tokens
Input from
$0.14
per 1M tokens
Output from
$0.28
per 1M tokens
Providers
3
automatic routing
Released
Apr 23, 2026
  • Streaming
  • Vision
  • Tools
  • Reasoning
  • JSON Output
  • Structured JSON
No ratings yetSign in to rate

Providers for MiMo V2.5

Compare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.

3 providers · select a column to sort

ProviderActions
Deactivated
262.1k16.4k$0.40$2.00$0.08
Deactivated
1.0M131.1k$0.168$0.336$0.0034
Deactivated
1M131.1k$0.14$0.28$0.0028

Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.

Frequently asked questions

What is MiMo V2.5?

Xiaomi's full-modal perception model supporting native understanding of images, videos, audio, and text with 1M context. Agent performance comparable to MiMo V2.5 Pro. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does MiMo V2.5 cost?

Pricing for MiMo V2.5 on LLM Gateway starts at $0.14 per million input tokens and $0.28 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of MiMo V2.5?

MiMo V2.5 supports a context window of up to 1,048,576 tokens on its largest provider deployment.

Which providers serve MiMo V2.5?

MiMo V2.5 is served by DeepInfra, NovitaAI, Xiaomi through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does MiMo V2.5 support tool calling and structured outputs?

Yes. MiMo V2.5 supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.

When was MiMo V2.5 released?

MiMo V2.5 was released on April 23, 2026.