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
nemotron-lightning-3.5-30b-a3b
kimi-k3 vs nemotron-lightning-3.5-30b-a3b
Output tokens cost $15.00 per million on kimi-k3 and $0.20 per million on nemotron-lightning-3.5-30b-a3b. Input tokens cost $3.00 per million on kimi-k3 and $0.05 per million on nemotron-lightning-3.5-30b-a3b. Cached input tokens are billed at $0.30 per million on kimi-k3 and $0.01 per million on nemotron-lightning-3.5-30b-a3b. Context lengths are 1,048,576 tokens on kimi-k3 and 262,000 tokens on nemotron-lightning-3.5-30b-a3b. Time to first token (TTFT) measured on AIHubMix is 2.4s on kimi-k3 and 0.2s on nemotron-lightning-3.5-30b-a3b. Measured output throughput is 39.1 tok/s on kimi-k3 and 108.1 tok/s on nemotron-lightning-3.5-30b-a3b.
kimi-k3nemotron-lightning-3.5-30b-a3b+ Add model · 2/4
nemotron-lightning-3.5-30b-a3b
Nvidia · text → text
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring 3 billion active parameters out of 30 billion total. It supports an extensive context window of up to 1,000,000 tokens. This model is designed to deliver efficient performance for high-throughput agentic workloads and specialized tasks. Compared with Nemotron 3 Super and Ultra, Lightning is smaller and optimized for fast, high-volume execution, while the larger models focus on complex planning and advanced reasoning.
Input$0.05 /M
Output$0.20 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
kimi-k3
nemotron-lightning-3.5-30b-a3b
Input /M
$3.00
$0.05
Output /M
$15.00
$0.20
Cache read /M
$0.30
$0.01
Context length
1,048,576
262,000
Max output
1,048,576
0
Time to First Token
2.4 s
0.2 s
Throughput
39.1 tok/s
108.1 tok/s
Modalities
textimagevideo
text
Supported Parameters
thinkingfunction callingstructured outputs
reasoningtool callinglong context
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-k3nemotron-lightning-3.5-30b-a3b
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3nemotron-lightning-3.5-30b-a3b
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
nemotron-lightning-3.5-30b-a3b
$6.00 /mo
kimi-k3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: kimi-k3, nemotron-lightning-3.5-30b-a3b?
nemotron-lightning-3.5-30b-a3b: $0.20/M output tokens; kimi-k3: $15.00/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
nemotron-lightning-3.5-30b-a3b: 0.2s 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 nemotron-lightning-3.5-30b-a3b accepts 262,000 input tokens.
Which one generates tokens faster?
nemotron-lightning-3.5-30b-a3b at 108.1 tok/s and kimi-k3 at 39.1 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; nemotron-lightning-3.5-30b-a3b accepts text input and supports reasoning, tool calling and long context.
Can I call kimi-k3 and nemotron-lightning-3.5-30b-a3b 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