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
Qwen3 Next 80B A3B Thinking
Kimi K3 vs Qwen3 Next 80B A3B Thinking
Compare Kimi K3 from Moonshot AI and Qwen3 Next 80B A3B Thinking 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 Next 80B A3B Thinking+ Add model · 2/4
Qwen3 Next 80B A3B Thinking
Qwen · text, image → text
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that excels by outputting structured 'thinking' traces (Chain-of-Thought) by default. Designed for hard, multi-step problems, it is ideal for tasks like math proofs, code synthesis, logic puzzles, and agentic planning. Compared to other Qwen3 variants, it offers greater stability during long reasoning chains and is tuned to follow complex instructions without getting repetitive or off-task. This model is perfectly suited for agent frameworks, tool use (function calling), and benchmarks where a step-by-step breakdown is required. It leverages throughput-oriented techniques for fast generation of detailed, procedural outputs.
Input$0.14 /M
Output$1.42 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen3 Next 80B A3B Thinking
Input /M
$3.00
$0.14
Output /M
$15.00
$1.42
Cache read /M
$0.30
$0.14
Context length
1,048,576
256,000
Max output
1,048,576
256,000
Time to First Token
0.9 s
0.5 s
Throughput
73.1 tok/s
211.9 tok/s
Modalities
textimagevideo
textimage
Supported Parameters
thinkingfunction callingstructured outputs
thinkingtoolsfunction callingstructured outputs
API Formats
Released
-
-
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-next-80b-a3b-thinking
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen3-next-80b-a3b-thinking
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3qwen3-next-80b-a3b-thinking
1300138014601540
Overall
13701486
Coding
14211531
Math
13901390
Hard prompts
13841505
Instruction following
13591479
Multi-turn
13501499
Creative writing
13241470
Longer query
13691502
Chinese
14141527
English
13871491
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 Next 80B A3B Thinking
$29.82 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen3 Next 80B A3B Thinking?
Qwen3 Next 80B A3B Thinking: $1.42/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; Qwen3 Next 80B A3B Thinking: 1421 (LMArena coding leaderboard).
Which responds faster?
Qwen3 Next 80B A3B Thinking: 0.5s 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 Qwen3 Next 80B A3B Thinking accepts 256,000 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 256,000 tokens on Qwen3 Next 80B A3B Thinking.
Which one generates tokens faster?
Qwen3 Next 80B A3B Thinking at 211.9 tok/s and Kimi K3 at 73.1 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; Qwen3 Next 80B A3B Thinking accepts text and image input and supports thinking, tool calling, function calling and structured outputs.
Can I call Kimi K3 and Qwen3 Next 80B A3B Thinking 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