MiMo V2.6 Pro

PRICE / USD

$0.435

Per 1 million output tokens · input billed separately

Input / 1M tokens

$0.435

Output / 1M tokens

$0.87

Cached input / 1M tokens

$0.0036

Cache write / 1M tokens

$0

Published USD rates, not a conversion of domestic CNY prices. Cache writes are temporarily free. Batch pricing and Token Plan subscriptions are separate; web search is billed additionally.

SPEED & CAPABILITIES

42.8 tokens/s

Xiaomi API · MiMo V2.6 Pro · reasoning model. Artificial Analysis reports a rolling 72-hour median of output speed after the first token, not total response time. Checked 2026-10-05; speed varies with workload and serving conditions.

Artificial Analysis · performance methodology v2.2.0 ↗ · Checked 2026-10-05. (fast) means median output above 150 tokens/s in these settings.

Model score

38

Our own output-speed measurement

Not measured

Context window

1,000,000

API model ID

mimo-v2.6-pro

Artificial Analysis tested MiMo V2.6 Pro · reasoning. This mostly English, text-based index is not a guarantee of performance on your workload. Artificial Analysis · MiMo V2.6 Pro · reasoning ↗

Conservative editorial adjustment: 38. Site owner's conservative placement near DeepSeek V4.1 Flash because benchmark scores may not transfer to real tasks; not an independent benchmark or a matched task evaluation.

Accepts text, image, video, and audio input; generates text. Video understanding is not video generation.

This entry covers regular Pro, not the separately priced Pro UltraSpeed endpoint. Its price and speed must not be mixed with that serving tier.

Suggested starting role: everyday coding. A lower-cost candidate for coding and agent workflows. Its reviewed Intelligence Index result is 46 versus DeepSeek V4.1 Flash at 39; test both on the same tasks before treating their practical quality as equivalent. This is editorial guidance, not a benchmark score.