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
Llama 3.3 70B
Kimi K3 vs Llama 3.3 70B
Compare Kimi K3 from Moonshot AI and Llama 3.3 70B 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 K3Llama 3.3 70B+ Add model · 2/4
Llama 3.3 70B
Llama · → text
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.
Input$0.6 /M
Output$0.6 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Llama 3.3 70B
Input /M
$3
$0.6
Output /M
$15
$0.6
Cache read /M
$0.3
-
Context length
1,048,576
65,536
Max output
1,048,576
8,192
Time to First Token
0.9 s
0.3 s
Throughput
73.1 tok/s
3250.0 tok/s
Modalities
textimagevideo
Supported Parameters
thinkingfunction callingstructured outputs
API Formats
Released
July 16, 2026
December 6, 2024
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-3.3-70b
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3llama-3.3-70b
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3llama-3.3-70b
1260134014201500
Overall
13181486
Coding
13451531
Math
12961296
Hard prompts
13211505
Instruction following
12921479
Multi-turn
13171499
Creative writing
12861470
Longer query
13121502
Chinese
12911527
English
13441491
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 3.3 70B
$45.00 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Llama 3.3 70B?
Llama 3.3 70B: $0.6/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; Llama 3.3 70B: 1345 (LMArena coding leaderboard).
Which responds faster?
Llama 3.3 70B: 0.3s 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 3.3 70B accepts 65,536 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 8,192 tokens on Llama 3.3 70B.
Which one generates tokens faster?
Llama 3.3 70B at 3250.0 tok/s and Kimi K3 at 73.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Can I call Kimi K3 and Llama 3.3 70B 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.
