coding-xiaomi-mimo-v2-omni
Xiaomi · text → text
Only supports OpenAI-compatible formats.
Input$0.08 /M
Output$0.40 /M
← Modelscoding-xiaomi-mimo-v2-omni
kimi-k3
coding-xiaomi-mimo-v2-omni vs kimi-k3
Output tokens cost $0.40 per million on coding-xiaomi-mimo-v2-omni and $15.00 per million on kimi-k3. Input tokens cost $0.08 per million on coding-xiaomi-mimo-v2-omni and $3.00 per million on kimi-k3. Cached input tokens are billed at $0.02 per million on coding-xiaomi-mimo-v2-omni and $0.30 per million on kimi-k3. On the LMArena coding leaderboard coding-xiaomi-mimo-v2-omni scores 1488 and kimi-k3 scores 1531.
coding-xiaomi-mimo-v2-omnikimi-k3+ Add model · 2/4
kimi-k3
Moonshot AI · text, image, video → text
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.
Input$3.00 /M
Output$15.00 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
coding-xiaomi-mimo-v2-omni
kimi-k3
Input /M
$0.08
$3.00
Output /M
$0.40
$15.00
Cache read /M
$0.02
$0.30
Context length
0
1,048,576
Max output
0
1,048,576
Time to First Token
-
12.9 s
Throughput
-
18.8 tok/s
Modalities
text
textimagevideo
Supported Parameters
thinkingtoolsfunction callingstructured outputs
thinkingfunction callingstructured outputs
API Formats
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.
coding-xiaomi-mimo-v2-omnikimi-k3
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
coding-xiaomi-mimo-v2-omnikimi-k3
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
coding-xiaomi-mimo-v2-omnikimi-k3
1380144015001560
Overall
14301486
Coding
14881531
Math
14371437
Hard prompts
14581505
Instruction following
14271479
Multi-turn
14501499
Creative writing
13961470
Longer query
14491502
Chinese
14841527
English
14451491
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.
coding-xiaomi-mimo-v2-omni
$10.80 /mo
kimi-k3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: coding-xiaomi-mimo-v2-omni, kimi-k3?
coding-xiaomi-mimo-v2-omni: $0.40/M output tokens; kimi-k3: $15.00/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
kimi-k3: 1531; coding-xiaomi-mimo-v2-omni: 1488 (LMArena coding leaderboard).
What inputs and capabilities does each model support?
coding-xiaomi-mimo-v2-omni accepts text input and supports thinking, tool calling, function calling and structured outputs; kimi-k3 accepts text, image and video input and supports thinking, function calling and structured outputs.
Can I call coding-xiaomi-mimo-v2-omni and kimi-k3 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.
AIHubMix