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
← ModelsKimi K3
Qwen2.5 VL 72B Instruct
Kimi K3 vs Qwen2.5 VL 72B Instruct
Output tokens cost $15.00 per million on Kimi K3 and $7.20 per million on Qwen2.5 VL 72B Instruct. Input tokens cost $3.00 per million on Kimi K3 and $2.40 per million on Qwen2.5 VL 72B Instruct. Cached input tokens are billed at $0.30 per million on Kimi K3 and $2.40 per million on Qwen2.5 VL 72B Instruct.
Kimi K3Qwen2.5 VL 72B Instruct+ Add model · 2/4
Qwen2.5 VL 72B Instruct
Qwen · text, image → text
Strong capability in Chinese domain recognition, comparable to ChatGPT-4.0.
Input$2.40 /M
Output$7.20 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen2.5 VL 72B Instruct
Input /M
$3.00
$2.40
Output /M
$15.00
$7.20
Cache read /M
$0.30
$2.40
Context length
1,048,576
0
Max output
1,048,576
0
Time to First Token
0.9 s
-
Throughput
73.1 tok/s
-
Modalities
textimagevideo
textimage
Supported Parameters
thinkingfunction callingstructured outputs
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.
kimi-k3qwen2.5-vl-72b-instruct
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen2.5-vl-72b-instruct
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
Qwen2.5 VL 72B Instruct
$252 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen2.5 VL 72B Instruct?
Qwen2.5 VL 72B Instruct: $7.20/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
What inputs and capabilities does each model support?
Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs; Qwen2.5 VL 72B Instruct accepts text and image input.
Can I call Kimi K3 and Qwen2.5 VL 72B Instruct 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