MiMo V2 Flash
MiMo V2 Flash is Xiaomi's language model with a 262K context window and up to 66K output tokens, available from 4 providers, starting at $0.100 / 1M input and $0.300 / 1M output. A highly efficient MoE LLM from Xiaomi with 309B total parameters and only 15B active, designed for extreme inference speed with hybrid attention.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 Hugging Face | $0.100 | $0.300 | N/A |
 Novita | $0.100 | $0.300 | $0.020 |
 OpenRouter | $0.100 | $0.300 | $0.010 |
 Vercel AI Gateway | $0.100 | $0.300 | $0.010 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MiMo V2.5 Pro | 1.1M | $1.00 | $3.00 | Available | |
| MiMo V2.5 | 1.1M | $0.400 | $2.00 | Available | |
| MiMo V2 Pro | 1.0M | $1.00 | $3.00 | Available | |
| MiMo V2 Omni | 262K | $0.400 | $2.00 | Available | |
| MiMo V2 Flash | 262K | $0.100 | $0.300 | Current | |
| MiMo V2.5 424B | — | — | — | — | Available |
| MiMo V2 Omni | — | — | — | — | Available |
| MiMo V2 | — | — | — | — | Available |
| MiMo V2 Flash Reasoning | — | — | — | — | Available |
| MiMo V2 TTS | — | — | — | — | Available |
| MiMo V2.5 TTS VoiceDesign | — | — | — | — | Available |