This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Xiaomi has launched a newer release, MiMo-V2.6-Pro. We suggest considering it instead.

Xiaomi logo
Xiaomi
•
MiMo-V2.5-Pro
•

Open weights model

•

Released April 2026

MiMo-V2.5-Pro (Reasoning) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of MiMo-V2.5-Pro (Reasoning) for your use-case.

Fastest

#1
ZyphraZyphra
81.0 t/s
#2
NovitaNovita
30.0 t/s
#3
XiaomiXiaomi
29.0 t/s
#4
DeepInfraDeepInfra
27.8 t/s

Output speed

Total 5 providers

Lowest Latency

#1
ZyphraZyphra
25.88 s
#2
NovitaNovita
69.12 s
#3
XiaomiXiaomi
71.46 s
#4
DeepInfraDeepInfra
73.86 s

Time to first answer token

Total 5 providers

Lowest Price

#1
GMIGMI
$0.14
#2
XiaomiXiaomi
$0.18
#3
NovitaNovita
$0.21
#4
DeepInfraDeepInfra
$0.25
#5
ZyphraZyphra
$0.51

Blended price (per 1M tokens)

Total 5 providers

MiMo-V2.5-Pro is available through 5 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For output speed, the top providers are Zyphra (81.0 t/s), Novita (30.0 t/s), and Xiaomi (29.0 t/s). Speed varies significantly across providers, with a 192% difference between the fastest and slowest.
  • For latency, Zyphra (25.88s), Novita (69.12s), and Xiaomi (71.46s) offer the lowest time to first answer token.
  • For pricing, GMI (0.14), Xiaomi (0.18), and Novita (0.21) offer the lowest blended prices per 1M tokens. Prices vary up to 3.7x across providers.
  • Zyphra offers the best performance with both the highest speed and lowest latency. For cost optimization, GMI provides the most competitive pricing.

Highlights

Speed

Output tokens per second · Higher is better

Latency

Seconds to first answer token received · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher is better

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Speed

Measured by Output Speed (tokens per second)

Output Speed: MiMo-V2.5-Pro (Reasoning)

Output speed: output tokens per second · 10,000 input tokens

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
Most attractive quadrant

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

Seconds to first token received · Lower is better · 10,000 input tokens

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Key Comparison Metrics & API Features

Novita logoNovita
1.05M
Open
$0.07
30
2.32
85.83
66.81
GMI logoGMI
1.05M
Open
--
--
--
--
--
DeepInfra logoDeepInfra
65.5k
Open
$0.28
26
2.09
97.60
76.40
Zyphra logoZyphra
1.05M
Open
$0.17
80
1.18
32.60
25.13
Xiaomi logoXiaomi
1M
Open
$0.05
31
2.47
83.86
65.11

Frequently Asked Questions

Common questions about MiMo-V2.5-Pro (Reasoning) providers