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
Qwen3 30B A3B Thinking 2507
Kimi K3 vs Qwen3 30B A3B Thinking 2507
Compare Kimi K3 from Moonshot AI and Qwen3 30B A3B Thinking 2507 from Qwen on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Kimi K3Qwen3 30B A3B Thinking 2507+ Add model · 2/4
Qwen3 30B A3B Thinking 2507
Qwen · → text
Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise. Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences. Enhanced 256K long-context understanding capabilities.
Input$0.12 /M
Output$1.2 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen3 30B A3B Thinking 2507
Input /M
$3
$0.12
Output /M
$15
$1.2
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
August 28, 2025
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-k3qwen3-30b-a3b-thinking-2507
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen3-30b-a3b-thinking-2507
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3qwen3-30b-a3b-thinking-2507
1260134014201500
Overall
13271486
Coding
13871531
Math
13531353
Hard prompts
13451505
Instruction following
13111479
Multi-turn
13211499
Creative writing
12851470
Longer query
13391502
Chinese
13711527
English
13461491
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.
Qwen3 30B A3B Thinking 2507
$25.20 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen3 30B A3B Thinking 2507?
Qwen3 30B A3B Thinking 2507: $1.2/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; Qwen3 30B A3B Thinking 2507: 1387 (LMArena coding leaderboard).
Can I call Kimi K3 and Qwen3 30B A3B Thinking 2507 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.
