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 /M
Output$15 /M
Cache read$0.3 /M
← ModelsKimi K3
meta-llama/Llama-3.2-90B-Vision-Instruct
Kimi K3 vs meta-llama/Llama-3.2-90B-Vision-Instruct
Compare Kimi K3 from Moonshot AI and meta-llama/Llama-3.2-90B-Vision-Instruct from Llama on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Kimi K3meta-llama/Llama-3.2-90B-Vision-Instruct+ Add model · 2/4
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
meta-llama/Llama-3.2-90B-Vision-Instruct
Input /M
$3
$0.5
Output /M
$15
$0.5
Cache read /M
$0.3
-
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
Supported Parameters
thinkingfunction callingstructured outputs
API Formats
Released
July 16, 2026
-
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-k3meta-llama/Llama-3.2-90B-Vision-Instruct
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3meta-llama/Llama-3.2-90B-Vision-Instruct
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3meta-llama/Llama-3.2-90B-Vision-Instruct
1100122013401460
Overall
11661486
Coding
11751531
Math
11651165
Hard prompts
11671505
Instruction following
11451479
Multi-turn
11481499
Creative writing
11441470
Longer query
11571502
Chinese
11281527
English
12241491
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.
meta-llama/Llama-3.2-90B-Vision-Instruct
$37.50 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, meta-llama/Llama-3.2-90B-Vision-Instruct?
meta-llama/Llama-3.2-90B-Vision-Instruct: $0.5/M output tokens; Kimi K3: $15/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Kimi K3: 1531; meta-llama/Llama-3.2-90B-Vision-Instruct: 1175 (LMArena coding leaderboard).
Can I call Kimi K3 and meta-llama/Llama-3.2-90B-Vision-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.
