MiMo-V2-Flash

huggingface/XiaomiMiMo/MiMo-V2-Flash · family mimo · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.15Blended $/1M (3:1)

$0.1Input $/1M

$0.3Output $/1M

$0.401M in + 1M out

—Cache read $/1M

#1059 of 5,000Cheapest rank

Provider: Hugging Face (huggingface)
Context: 262,144 tokens
Max output: 4,096 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“MiMo-V2-Flash” is offered by 4 providers — cheapest-effective first. This one (Hugging Face) is the cheapest.

Provider	Input	Output	Blended	Context
Hugging Face (this)	$0.1	$0.3	$0.15	262k
ZenMux	$0.1	$0.3	$0.15	262k
Qiniu	$0.1	$0.3	$0.15	256k
Xiaomi	$0.14	$0.28	$0.18	262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Hugging Face and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"XiaomiMiMo/MiMo-V2-Flash","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):