MiMo-V2-Flash API

Designed for modern AI workloads, MiMo-V2-Flash is equally suited for reasoning-heavy tasks, software engineering, agent orchestration, and large-document understanding.
Output

How to use MiMo-V2-Flash API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to .

OpenAI-compatible — swap the base URL and it works with your existing SDK.

MiMo-V2-Flash API Pricing

TypePrice
Input
Output

MiMo-V2-Flash Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
22.4
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

MiMo-V2-Flash vs other models

ModelInputOutputContextBest for
MiMo-V2-Flash
This page
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Yes, MiMo-V2-Flash can stream responses as they are generated.

Yes, MiMo-V2-Flash supports both function calling and structured outputs.

MiMo-V2-Flash was built by Xiaomi.

Yes, MiMo-V2-Flash is available through the v1 endpoint.

MiMo-V2-Flash is accessed via the v1 endpoint.

Start building with MiMo-V2-Flash

Get API Key
1000+ models, one API.