Models

DeepSeek V3.2 Thinking vs Kimi K3

Compare DeepSeek V3.2 Thinking from DeepSeek and Kimi K3 from Moonshot AI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.

DeepSeekDeepSeek V3.2 ThinkingMoonshot AIKimi K3
DeepSeek logo
DeepSeek V3.2 Thinking
DeepSeek · text → text

DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse Attention and reinforced reasoning performance, but its core strength lies in powerful agentic capabilities—enabled by large-scale task-synthesis that tightly integrates reasoning with real-world tool use, delivering robust, compliant, and generalizable agent behaviour. Users can toggle deeper reasoning through the reasoning_enabled switch.

Input$0.30 /M
Output$0.45 /M
Moonshot AI logo
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 V3.2 Thinking
Kimi K3
Input /M
$0.30
$3.00
Output /M
$0.45
$15.00
Cache read /M
$0.03
$0.30
Context length
128,000
1,048,576
Max output
64,000
1,048,576
Time to First Token
3.6 s
0.9 s
Throughput
31.0 tok/s
73.1 tok/s
Modalities
text
textimagevideo
Supported Parameters
toolsfunction callingstructured outputsthinking
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-v3.2-thinkkimi-k3

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

deepseek-v3.2-thinkkimi-k3

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
deepseek-v3.2-thinkkimi-k3
1360142014801540
Overall
14231486
Coding
14751531
Math
14261426
Hard prompts
14461505
Instruction following
14191479
Multi-turn
14271499
Creative writing
13921470
Longer query
14421502
Chinese
14671527
English
14441491

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 V3.2 Thinking
$24.92 /mo
Kimi K3
$405 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: DeepSeek V3.2 Thinking, Kimi K3?

DeepSeek V3.2 Thinking: $0.45/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 V3.2 Thinking: 1475 (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 V3.2 Thinking accepts 128,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 64,000 tokens on DeepSeek V3.2 Thinking and 1,048,576 tokens on Kimi K3.

Which one generates tokens faster?

Kimi K3 at 73.1 tok/s and DeepSeek V3.2 Thinking at 31.0 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 V3.2 Thinking accepts text input and supports tool calling, function calling, structured outputs and thinking; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.

Can I call DeepSeek V3.2 Thinking 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.