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 397B A17B
Kimi K3 vs Qwen3.5 397B A17B
Compare Kimi K3 from Moonshot AI and Qwen3.5 397B A17B 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 K3Qwen3.5 397B A17B+ Add model · 2/4
Qwen3.5 397B A17B
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$0.16 /M
Output$0.99 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen3.5 397B A17B
Input /M
$3.00
$0.16
Output /M
$15.00
$0.99
Cache read /M
$0.30
$0.16
Context length
1,048,576
991,000
Max output
1,048,576
64,000
Time to First Token
0.9 s
1.7 s
Throughput
73.1 tok/s
30.4 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-k3qwen3.5-397b-a17b
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen3.5-397b-a17b
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3qwen3.5-397b-a17b
1380144015001560
Overall
14421486
Coding
14911531
Math
14491449
Hard prompts
14631505
Instruction following
14351479
Multi-turn
14531499
Creative writing
14061470
Longer query
14541502
Chinese
14991527
English
14491491
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 397B A17B
$24.66 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen3.5 397B A17B?
Qwen3.5 397B A17B: $0.99/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 397B A17B: 1491 (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 397B A17B accepts 991,000 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 64,000 tokens on Qwen3.5 397B A17B.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and Qwen3.5 397B A17B at 30.4 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 397B A17B 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 397B A17B 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