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
Kimi K3 vs Qwen3 235B A22B
Output tokens cost $15.00 per million on Kimi K3 and $1.12 per million on Qwen3 235B A22B. Input tokens cost $3.00 per million on Kimi K3 and $0.28 per million on Qwen3 235B A22B. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.28 per million on Qwen3 235B A22B. Context lengths are 1,048,576 tokens on Kimi K3 and 131,100 tokens on Qwen3 235B A22B. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 0.6s on Qwen3 235B A22B. Measured output throughput is 73.1 tok/s on Kimi K3 and 81.2 tok/s on Qwen3 235B A22B. On the LMArena coding leaderboard Kimi K3 scores 1531 and Qwen3 235B A22B scores 1433.
Kimi K3Qwen3 235B A22B+ Add model · 2/4
Qwen3 235B A22B
Qwen · text → text
Qwen3-235B-A22B is a massive 235B parameter Mixture-of-Experts (MoE) model that operates with the efficiency of a 22B model. Its standout feature is the ability to seamlessly switch between a "thinking" mode for complex reasoning and a "non-thinking" mode for fast conversation, offering both world-class power and practical speed.
Input$0.28 /M
Output$1.12 /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
Input /M
$3.00
$0.28
Output /M
$15.00
$1.12
Cache read /M
$0.30
$0.28
Context length
1,048,576
131,100
Max output
1,048,576
128,000
Time to First Token
0.9 s
0.6 s
Throughput
73.1 tok/s
81.2 tok/s
Modalities
textimagevideo
text
Supported Parameters
thinkingfunction callingstructured outputs
toolsfunction 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
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
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
1300138014601540
Overall
13751486
Coding
14331531
Math
13921392
Hard prompts
13911505
Instruction following
13571479
Multi-turn
13711499
Creative writing
13241470
Longer query
13781502
Chinese
13921527
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 235B A22B
$33.60 /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?
Qwen3 235B A22B: $1.12/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: 1433 (LMArena coding leaderboard).
Which responds faster?
Qwen3 235B A22B: 0.6s 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 accepts 131,100 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 128,000 tokens on Qwen3 235B A22B.
Which one generates tokens faster?
Qwen3 235B A22B at 81.2 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 accepts text input and supports tool calling, function calling and structured outputs.
Can I call Kimi K3 and Qwen3 235B A22B 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