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 122B A10B
Kimi K3 vs Qwen3.5 122B A10B
Output tokens cost $15.00 per million on Kimi K3 and $0.90 per million on Qwen3.5 122B A10B. Input tokens cost $3.00 per million on Kimi K3 and $0.11 per million on Qwen3.5 122B A10B. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.11 per million on Qwen3.5 122B A10B. Context lengths are 1,048,576 tokens on Kimi K3 and 991,000 tokens on Qwen3.5 122B A10B. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 1.5s on Qwen3.5 122B A10B. Measured output throughput is 73.1 tok/s on Kimi K3 and 61.8 tok/s on Qwen3.5 122B A10B. On the LMArena coding leaderboard Kimi K3 scores 1531 and Qwen3.5 122B A10B scores 1459.
Kimi K3Qwen3.5 122B A10B+ Add model · 2/4
Qwen3.5 122B A10B
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$0.11 /M
Output$0.90 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen3.5 122B A10B
Input /M
$3.00
$0.11
Output /M
$15.00
$0.90
Cache read /M
$0.30
$0.11
Context length
1,048,576
991,000
Max output
1,048,576
64,000
Time to First Token
0.9 s
1.5 s
Throughput
73.1 tok/s
61.8 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-k3qwen3.5-122b-a10b
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen3.5-122b-a10b
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3qwen3.5-122b-a10b
1340140014601520
Overall
14171486
Coding
14591531
Math
14231423
Hard prompts
14331505
Instruction following
14071479
Multi-turn
14181499
Creative writing
13671470
Longer query
14191502
Chinese
14611527
English
14311491
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 122B A10B
$20.27 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen3.5 122B A10B?
Qwen3.5 122B A10B: $0.90/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 122B A10B: 1459 (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 122B A10B accepts 991,000 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 64,000 tokens on Qwen3.5 122B A10B.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and Qwen3.5 122B A10B at 61.8 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 122B A10B 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 122B A10B 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