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
llama-4-maverick
kimi-k3 vs llama-4-maverick
Output tokens cost $15.00 per million on kimi-k3 and $0.20 per million on llama-4-maverick. Input tokens cost $3.00 per million on kimi-k3 and $0.20 per million on llama-4-maverick. Cached input tokens are billed at $0.30 per million on kimi-k3 and $0.20 per million on llama-4-maverick. Context lengths are 1,048,576 tokens on kimi-k3 and 1,048,576 tokens on llama-4-maverick. Time to first token (TTFT) measured on AIHubMix is 12.9s on kimi-k3 and 0.2s on llama-4-maverick. Measured output throughput is 18.8 tok/s on kimi-k3 and 97.8 tok/s on llama-4-maverick. On the LMArena coding leaderboard kimi-k3 scores 1531 and llama-4-maverick scores 1373.
kimi-k3llama-4-maverick+ Add model · 2/4
llama-4-maverick
Llama · text, image → text
Llama 4 Maverick is a high-capacity Mixture-of-Experts (MoE) model from Meta, featuring 400B total parameters and 128 experts, while activating an efficient 17B parameters per inference. Engineered for peak performance, it excels at advanced multimodal tasks. Maverick natively supports text and image input, producing multilingual text and code. With a 1-million-token context window and instruction tuning, it is optimized for complex image reasoning and general-purpose assistant-like interactions. Released under the Llama 4 Community License, Maverick is ideal for research and commercial applications demanding state-of-the-art multimodal understanding and high throughput.
Input$0.20 /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
llama-4-maverick
Input /M
$3.00
$0.20
Output /M
$15.00
$0.20
Cache read /M
$0.30
$0.20
Context length
1,048,576
1,048,576
Max output
1,048,576
32,000
Time to First Token
12.9 s
0.2 s
Throughput
18.8 tok/s
97.8 tok/s
Modalities
textimagevideo
textimage
Supported Parameters
thinkingfunction callingstructured outputs
toolsfunction 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.
kimi-k3llama-4-maverick
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3llama-4-maverick
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3llama-4-maverick
1280136014401520
Overall
13271486
Coding
13731531
Math
13191319
Hard prompts
13381505
Instruction following
13141479
Multi-turn
13241499
Creative writing
13071470
Longer query
13341502
Chinese
13301527
English
13401491
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.
llama-4-maverick
$15.00 /mo
kimi-k3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: kimi-k3, llama-4-maverick?
llama-4-maverick: $0.20/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; llama-4-maverick: 1373 (LMArena coding leaderboard).
Which responds faster?
llama-4-maverick: 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 llama-4-maverick accepts 1,048,576 input tokens. Maximum output per request is 1,048,576 tokens on kimi-k3 and 32,000 tokens on llama-4-maverick.
Which one generates tokens faster?
llama-4-maverick at 97.8 tok/s and kimi-k3 at 18.8 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; llama-4-maverick accepts text and image input and supports tool calling, function calling and structured outputs.
Can I call kimi-k3 and llama-4-maverick 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