MiMo V2 Pro vs Qwen3.8 Max Preview

Output tokens cost $3.30 per million on MiMo V2 Pro and $1.01 per million on Qwen3.8 Max Preview. Input tokens cost $1.10 per million on MiMo V2 Pro and $0.34 per million on Qwen3.8 Max Preview. Cached input tokens are billed at $0.22 per million on MiMo V2 Pro and $0.03 per million on Qwen3.8 Max Preview. Context lengths are 1,000,000 tokens on MiMo V2 Pro and 983,616 tokens on Qwen3.8 Max Preview. Time to first token (TTFT) measured on AIHubMix is 1.7s on MiMo V2 Pro and 2.4s on Qwen3.8 Max Preview. Measured output throughput is 41.3 tok/s on MiMo V2 Pro and 48.1 tok/s on Qwen3.8 Max Preview. On the LMArena coding leaderboard MiMo V2 Pro scores 1503 and Qwen3.8 Max Preview scores 1520.

MiMo V2 Pro Qwen

Qwen3.8 Max Preview

+ Add model · 2/4

MiMo V2 Pro

Xiaomi · text, image, video, audio → text

Xiaomi MiMo-V2-Pro is built for high-intensity agent work scenarios in the real world. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M-token context length. On top of a powerful model foundation, we continuously scale compute across broader agent scenarios, further expanding the intelligent action space and achieving significant generalization from Coding to Claw.

Input$1.10 /M

Output$3.30 /M

Details

Qwen3.8 Max Preview

Qwen · text, image → text

Qwen 3.8 Max Preview(Qwen3.8-Max-Preview) is the latest-generation foundation model in the Qwen family, packing 2.4T parameters and still evolving. Compared with the previous flagship Qwen 3.7 Max, it delivers major gains in core capabilities like Coding and Cowork (professional productivity), with world-leading performance on complex, long-horizon tasks such as full-stack development, data analysis, and Office workflows. Launch offer: Credits are consumed at just 20% of the standard rate, effectively 5× your usage. Limited time only.

Input$0.34 /M

Output$1.01 /M

Details

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

MiMo V2 Pro

Qwen3.8 Max Preview

Input /M

$1.10

$0.34

Output /M

$3.30

$1.01

Cache read /M

$0.22

$0.03

Context length

1,000,000

983,616

Max output

131,072

Time to First Token

1.7 s

2.4 s

Throughput

41.3 tok/s

48.1 tok/s

Modalities

textimagevideoaudio

textimage

Supported Parameters

web

toolsfunction callingstructured outputsweblong contextthinking

API Formats

Released

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

mimo-v2-proqwen3.8-max-preview

Tokens / day

Requests / day

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

mimo-v2-proqwen3.8-max-preview

Throughput (tok/s)

TTFT (s)

Uptime (%)

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text

mimo-v2-proqwen3.8-max-preview

1400146015201580

Overall

14481481

Coding

15031520

Math

14521504

Hard prompts

14761506

Instruction following

14451478

Multi-turn

14701496

Creative writing

14251469

Longer query

14671497

Chinese

14831545

English

14651486

WebDev Arena

mimo-v2-proqwen3.8-max-preview

1400150016001700

Overall

14321669

React

14241678

HTML

14381628

Gaming

17331733

Simulations

16651665

Data analytics

16141614

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

Requests / day

Avg input tokens / request

Avg output tokens / request

Qwen3.8 Max Preview

$35.49 /mo

MiMo V2 Pro

$116 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: MiMo V2 Pro, Qwen3.8 Max Preview?

Qwen3.8 Max Preview: $1.01/M output tokens; MiMo V2 Pro: $3.30/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Qwen3.8 Max Preview: 1520; MiMo V2 Pro: 1503 (LMArena coding leaderboard).

Which responds faster?

MiMo V2 Pro: 1.7s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

MiMo V2 Pro accepts 1,000,000 and Qwen3.8 Max Preview accepts 983,616 input tokens.

Which one generates tokens faster?

Qwen3.8 Max Preview at 48.1 tok/s and MiMo V2 Pro at 41.3 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

MiMo V2 Pro accepts text, image, video and audio input and supports web search; Qwen3.8 Max Preview accepts text and image input and supports tool calling, function calling, structured outputs, web search, long context and thinking.

Can I call MiMo V2 Pro and Qwen3.8 Max Preview with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.

kimi-k3vsqwen3.8-max-preview claude-opus-5vsgpt-5.6-luna claude-opus-5vsclaude-sonnet-5 gemini-3.1-pro-previewvsgpt-5.5 glm-5.2vskimi-k3 gemini-3.6-flashvsqwen3.8-max deepseek-v4-flashvsglm-5.2 claude-opus-5vsgrok-4.5

MiMo V2 Pro vs Qwen3.8 Max Preview

Pricing & Specifications

Activity Past 30 Days

Tokens / day

Requests / day

Performance Past 3 Days

Throughput (tok/s)

TTFT (s)

Uptime (%)

LMArena Benchmarks

Cost calculator

FAQ

Popular comparisons

Product

Company

Developer

Connect