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
mai-thinking-1
kimi-k3 vs mai-thinking-1
Output tokens cost $15.00 per million on kimi-k3 and $8.00 per million on mai-thinking-1. Input tokens cost $3.00 per million on kimi-k3 and $2.00 per million on mai-thinking-1. Cached input tokens are billed at $0.30 per million on kimi-k3 and $2.00 per million on mai-thinking-1. Context lengths are 1,048,576 tokens on kimi-k3 and 256,000 tokens on mai-thinking-1. Time to first token (TTFT) measured on AIHubMix is 0.9s on kimi-k3 and 6.7s on mai-thinking-1. Measured output throughput is 73.1 tok/s on kimi-k3 and 41.7 tok/s on mai-thinking-1.
kimi-k3mai-thinking-1+ Add model · 2/4
mai-thinking-1
Microsoft · text → text
MAI-Thinking-1 is Microsoft’s first inference model in the MAI series, built for enterprise-scale workloads. With excellent reasoning, mathematical, and general intelligence capabilities, combined with superior cost-effectiveness, it makes high-throughput, 24/7 AI workloads economically viable.
Input$2.00 /M
Output$8.00 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
kimi-k3
mai-thinking-1
Input /M
$3.00
$2.00
Output /M
$15.00
$8.00
Cache read /M
$0.30
$2.00
Context length
1,048,576
256,000
Max output
1,048,576
256,000
Time to First Token
0.9 s
6.7 s
Throughput
73.1 tok/s
41.7 tok/s
Modalities
textimagevideo
text
Supported Parameters
thinkingfunction callingstructured outputs
thinkingstructured outputs
API Formats
chat_completions
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-k3mai-thinking-1
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3mai-thinking-1
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
mai-thinking-1
$240 /mo
kimi-k3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: kimi-k3, mai-thinking-1?
mai-thinking-1: $8.00/M output tokens; kimi-k3: $15.00/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
kimi-k3: 0.9s 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?
kimi-k3 accepts 1,048,576 and mai-thinking-1 accepts 256,000 input tokens. Maximum output per request is 1,048,576 tokens on kimi-k3 and 256,000 tokens on mai-thinking-1.
Which one generates tokens faster?
kimi-k3 at 73.1 tok/s and mai-thinking-1 at 41.7 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
kimi-k3 accepts text, image and video input and supports thinking, function calling and structured outputs; mai-thinking-1 accepts text input and supports thinking and structured outputs.
Can I call kimi-k3 and mai-thinking-1 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