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-3.1-405b-instruct
Kimi K3 vs meta/llama-3.1-405b-instruct
Compare Kimi K3 from Moonshot AI and meta/llama-3.1-405b-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-3.1-405b-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-3.1-405b-instruct
Input /M
$3
$5
Output /M
$15
$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-3.1-405b-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-3.1-405b-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-3.1-405b-instruct
1280136014401520
Overall
13351486
Coding
13751531
Math
13151315
Hard prompts
13411505
Instruction following
13131479
Multi-turn
13391499
Creative writing
13011470
Longer query
13271502
Chinese
13211527
English
13611491
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-3.1-405b-instruct
$375 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, meta/llama-3.1-405b-instruct?
meta/llama-3.1-405b-instruct: $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-3.1-405b-instruct: 1375 (LMArena coding leaderboard).
Can I call Kimi K3 and meta/llama-3.1-405b-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.
