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
muse-spark-1.1
kimi-k3 vs muse-spark-1.1
Output tokens cost $15.00 per million on kimi-k3 and $4.68 per million on muse-spark-1.1. Input tokens cost $3.00 per million on kimi-k3 and $1.38 per million on muse-spark-1.1. Cached input tokens are billed at $0.30 per million on kimi-k3 and $1.38 per million on muse-spark-1.1. Context lengths are 1,048,576 tokens on kimi-k3 and 1,000,000 tokens on muse-spark-1.1. Time to first token (TTFT) measured on AIHubMix is 12.9s on kimi-k3 and 5.9s on muse-spark-1.1. Measured output throughput is 18.8 tok/s on kimi-k3 and 183.7 tok/s on muse-spark-1.1. On the LMArena coding leaderboard kimi-k3 scores 1531 and muse-spark-1.1 scores 1531.
kimi-k3muse-spark-1.1+ Add model · 2/4
muse-spark-1.1
Meta · text, image, audio, video → text
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.
Input$1.38 /M
Output$4.68 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
kimi-k3
muse-spark-1.1
Input /M
$3.00
$1.38
Output /M
$15.00
$4.68
Cache read /M
$0.30
$1.38
Context length
1,048,576
1,000,000
Max output
1,048,576
0
Time to First Token
12.9 s
5.9 s
Throughput
18.8 tok/s
183.7 tok/s
Modalities
textimagevideo
textimageaudiovideo
Supported Parameters
thinkingfunction callingstructured outputs
thinkingtools
API Formats
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-k3muse-spark-1.1
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3muse-spark-1.1
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3muse-spark-1.1
1420146015001540
Overall
14861489
Coding
15311531
Math
14881488
Hard prompts
15051509
Instruction following
14741479
Multi-turn
14971499
Creative writing
14461470
Longer query
14781502
Chinese
15271536
English
14901491
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.
muse-spark-1.1
$153 /mo
kimi-k3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: kimi-k3, muse-spark-1.1?
muse-spark-1.1: $4.68/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; muse-spark-1.1: 1531 (LMArena coding leaderboard).
Which responds faster?
muse-spark-1.1: 5.9s 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 muse-spark-1.1 accepts 1,000,000 input tokens.
Which one generates tokens faster?
muse-spark-1.1 at 183.7 tok/s and kimi-k3 at 18.8 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; muse-spark-1.1 accepts text, image, audio and video input and supports thinking and tool calling.
Can I call kimi-k3 and muse-spark-1.1 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