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
Qwen3.5 35B A3B
Kimi K3 vs Qwen3.5 35B A3B
Output tokens cost $15.00 per million on Kimi K3 and $0.45 per million on Qwen3.5 35B A3B. Input tokens cost $3.00 per million on Kimi K3 and $0.06 per million on Qwen3.5 35B A3B. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.06 per million on Qwen3.5 35B A3B. Context lengths are 1,048,576 tokens on Kimi K3 and 991,000 tokens on Qwen3.5 35B A3B. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 1.3s on Qwen3.5 35B A3B. Measured output throughput is 73.1 tok/s on Kimi K3 and 70.6 tok/s on Qwen3.5 35B A3B. On the LMArena coding leaderboard Kimi K3 scores 1531 and Qwen3.5 35B A3B scores 1435.
Kimi K3Qwen3.5 35B A3B+ Add model · 2/4
Qwen3.5 35B A3B
Qwen · text, image, video → text
The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.
Input$0.06 /M
Output$0.45 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen3.5 35B A3B
Input /M
$3.00
$0.06
Output /M
$15.00
$0.45
Cache read /M
$0.30
$0.06
Context length
1,048,576
991,000
Max output
1,048,576
64,000
Time to First Token
0.9 s
1.3 s
Throughput
73.1 tok/s
70.6 tok/s
Modalities
textimagevideo
textimagevideo
Supported Parameters
thinkingfunction callingstructured outputs
toolsfunction callingstructured outputsweblong contextthinking
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-k3qwen3.5-35b-a3b
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen3.5-35b-a3b
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3qwen3.5-35b-a3b
13201380144015001560
Overall
13951486
Coding
14351531
Math
14001400
Hard prompts
14131505
Instruction following
13891479
Multi-turn
13941499
Creative writing
13441470
Longer query
14021502
Chinese
14581527
English
14111491
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.
Qwen3.5 35B A3B
$10.15 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen3.5 35B A3B?
Qwen3.5 35B A3B: $0.45/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; Qwen3.5 35B A3B: 1435 (LMArena coding leaderboard).
Which responds faster?
Kimi K3: 0.9s 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 Qwen3.5 35B A3B accepts 991,000 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 64,000 tokens on Qwen3.5 35B A3B.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and Qwen3.5 35B A3B at 70.6 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; Qwen3.5 35B A3B accepts text, image and video input and supports tool calling, function calling, structured outputs, web search, long context and thinking.
Can I call Kimi K3 and Qwen3.5 35B A3B 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