•

Open weights model

•

Released September 2026

MiMo-V2.6-Pro API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of MiMo-V2.6-Pro for your use-case.

Lowest Time per Task

#1
PrimaLabsPrimaLabs
7.9 min
#2
DeepInfraDeepInfra
31.9 min
#3
XiaomiXiaomi
37.1 min
#4
GMI (BF16)GMI (BF16)
40.6 min

Time per Intelligence Index task (minutes)

Total 4 providers

Lowest Cost per Task

#1
GMI (BF16)GMI (BF16)
$0.19
#2
XiaomiXiaomi
$0.26
#3
DeepInfraDeepInfra
$0.54
#4
PrimaLabsPrimaLabs
$2.56

Cost per Intelligence Index task

Total 4 providers

MiMo-V2.6-Pro is available through 4 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For time per task, PrimaLabs (7.9 min), DeepInfra (31.9 min), and Xiaomi (37.1 min) finish an Intelligence Index task fastest.
  • For cost per task, GMI (BF16) ($0.19), Xiaomi ($0.26), and DeepInfra ($0.54) are the cheapest per Intelligence Index task. Cost varies up to 13.5x across providers.
Inference time (minutes) per Intelligence Index task · Lower is better
Weighted average cost (USD) per Intelligence Index task · Lower is better

Pricing

Cost per Intelligence Index Task: MiMo-V2.6-Pro

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Pricing: Cache Hit, Input, and Output: MiMo-V2.6-Pro

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: MiMo-V2.6-Pro

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
Most attractive quadrant
Pareto line

Speed

Average of the single-request and multi-turn agentic workloads measured

Time per Intelligence Index Task: MiMo-V2.6-Pro

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: MiMo-V2.6-Pro

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: MiMo-V2.6-Pro

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Caching

Cache Hit Rate: MiMo-V2.6-Pro

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate: MiMo-V2.6-Pro

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant

Key Comparison Metrics & API Features

DeepInfra logoDeepInfra
$0.54
37.6
42.20
2.6%
1M
Open
GMI logoGMI
$0.19
58.7
42.15
23.5%
1M
Open
PrimaLabs logoPrimaLabs
$2.56
9.0
10.62
0.0%
1M
Open
Xiaomi logoXiaomi
$0.26
35.7
38.67
0.6%
1M
Open

Frequently Asked Questions

Common questions about MiMo-V2.6-Pro providers