Claude 3 Sonnet 20240229
Anthropic · text, image → text
Input$3.30 /M
Output$16.50 /M
← ModelsClaude 3 Sonnet 20240229
Kimi K3
Claude 3 Sonnet 20240229 vs Kimi K3
Output tokens cost $16.50 per million on Claude 3 Sonnet 20240229 and $15.00 per million on Kimi K3. Input tokens cost $3.30 per million on Claude 3 Sonnet 20240229 and $3.00 per million on Kimi K3. Cached input tokens are billed at $3.30 per million on Claude 3 Sonnet 20240229 and $0.30 per million on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 0.8s on Claude 3 Sonnet 20240229 and 0.9s on Kimi K3. Measured output throughput is 66.6 tok/s on Claude 3 Sonnet 20240229 and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard Claude 3 Sonnet 20240229 scores 1317 and Kimi K3 scores 1531.
Claude 3 Sonnet 20240229Kimi K3+ Add model · 2/4
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
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Claude 3 Sonnet 20240229
Kimi K3
Input /M
$3.30
$3.00
Output /M
$16.50
$15.00
Cache read /M
$3.30
$0.30
Context length
NaN
1,048,576
Max output
0
1,048,576
Time to First Token
0.8 s
0.9 s
Throughput
66.6 tok/s
73.1 tok/s
Modalities
textimage
textimagevideo
Supported Parameters
thinkingfunction 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.
claude-3-sonnet-20240229kimi-k3
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
claude-3-sonnet-20240229kimi-k3
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
claude-3-sonnet-20240229kimi-k3
1220132014201520
Overall
12801486
Coding
13171531
Math
12531253
Hard prompts
12811505
Instruction following
12671479
Multi-turn
12771499
Creative writing
12451470
Longer query
12851502
Chinese
12751527
English
12881491
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.
Kimi K3
$405 /mo
Claude 3 Sonnet 20240229
$446 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Claude 3 Sonnet 20240229, Kimi K3?
Kimi K3: $15.00/M output tokens; Claude 3 Sonnet 20240229: $16.50/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Kimi K3: 1531; Claude 3 Sonnet 20240229: 1317 (LMArena coding leaderboard).
Which responds faster?
Claude 3 Sonnet 20240229: 0.8s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and Claude 3 Sonnet 20240229 at 66.6 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
Claude 3 Sonnet 20240229 accepts text and image input; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.
Can I call Claude 3 Sonnet 20240229 and Kimi K3 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