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 235B A22B Thinking 2507
Kimi K3 vs Qwen3 235B A22B Thinking 2507
Compare Kimi K3 from Moonshot AI and Qwen3 235B A22B 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 235B A22B Thinking 2507+ Add model · 2/4
Qwen3 235B A22B Thinking 2507
Qwen · text, image → text
The open-source thinking model based on Qwen3 has significantly improved in logical ability, general capability, knowledge enhancement, and creative ability compared to the previous version (Tongyi Qianwen 3-235B-A22B). It is suitable for high-difficulty and strong reasoning scenarios.
Input$0.28 /M
Output$2.80 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen3 235B A22B Thinking 2507
Input /M
$3.00
$0.28
Output /M
$15.00
$2.80
Cache read /M
$0.30
$0.28
Context length
1,048,576
262,144
Max output
1,048,576
262,144
Time to First Token
0.9 s
0.3 s
Throughput
73.1 tok/s
107.6 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-k3qwen3-235b-a22b-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-k3qwen3-235b-a22b-thinking-2507
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3qwen3-235b-a22b-thinking-2507
1340140014601520
Overall
13991486
Coding
14421531
Math
13981398
Hard prompts
14181505
Instruction following
13861479
Multi-turn
13941499
Creative writing
13741470
Longer query
14011502
Chinese
14481527
English
14051491
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 235B A22B Thinking 2507
$58.80 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen3 235B A22B Thinking 2507?
Qwen3 235B A22B Thinking 2507: $2.80/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 235B A22B Thinking 2507: 1442 (LMArena coding leaderboard).
Which responds faster?
Qwen3 235B A22B Thinking 2507: 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 Qwen3 235B A22B Thinking 2507 accepts 262,144 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 262,144 tokens on Qwen3 235B A22B Thinking 2507.
Which one generates tokens faster?
Qwen3 235B A22B Thinking 2507 at 107.6 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 235B A22B Thinking 2507 accepts text and image input and supports thinking, tool calling, function calling and structured outputs.
Can I call Kimi K3 and Qwen3 235B A22B 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.
AIHubMix