DeepSeek V3
DeepSeek · text → text
It has been automatically upgraded to the latest released version, 250324. Automatically upgraded to the latest released version 250324.
Input$0.27 /M
Output$1.09 /M
← ModelsDeepSeek V3
Kimi K3
DeepSeek V3 vs Kimi K3
Output tokens cost $1.09 per million on DeepSeek V3 and $15.00 per million on Kimi K3. Input tokens cost $0.27 per million on DeepSeek V3 and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.27 per million on DeepSeek V3 and $0.30 per million on Kimi K3. Context lengths are 1,638,000 tokens on DeepSeek V3 and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 1.2s on DeepSeek V3 and 0.9s on Kimi K3. Measured output throughput is 66.5 tok/s on DeepSeek V3 and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard DeepSeek V3 scores 1388 and Kimi K3 scores 1531.
DeepSeek V3Kimi 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.
DeepSeek V3
Kimi K3
Input /M
$0.27
$3.00
Output /M
$1.09
$15.00
Cache read /M
$0.27
$0.30
Context length
1,638,000
1,048,576
Max output
1,638,000
1,048,576
Time to First Token
1.2 s
0.9 s
Throughput
66.5 tok/s
73.1 tok/s
Modalities
text
textimagevideo
Supported Parameters
toolsfunction callingstructured outputs
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.
DeepSeek-V3kimi-k3
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
DeepSeek-V3kimi-k3
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
DeepSeek-V3kimi-k3
1280136014401520
Overall
13591486
Coding
13881531
Math
13111311
Hard prompts
13501505
Instruction following
13441479
Multi-turn
13741499
Creative writing
13491470
Longer query
13751502
Chinese
13691527
English
13711491
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.
DeepSeek V3
$32.64 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: DeepSeek V3, Kimi K3?
DeepSeek V3: $1.09/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; DeepSeek V3: 1388 (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?
DeepSeek V3 accepts 1,638,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 1,638,000 tokens on DeepSeek V3 and 1,048,576 tokens on Kimi K3.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and DeepSeek V3 at 66.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
DeepSeek V3 accepts text input and supports tool calling, function calling and structured outputs; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.
Can I call DeepSeek V3 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