← Models

Gemini 4 Carbon vs Kimi K3

Compare Gemini 4 Carbon from Google 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.

GoogleGemini 4 CarbonMoonshot AIKimi K3
Google logo
Gemini 4 Carbon
Google · text, image, video, audio, pdf → text

Gemini 4 Carbon is Google DeepMind’s multimodal model for complex coding, long-running agent workflows, and cybersecurity defense. Building on Gemini 4 Argon, it improves software engineering, vulnerability detection and remediation, multimodal understanding, and execution across challenging, multi-step tasks.

Input$2 /M
Output$10 /M
Cache read$0.1 /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$2.84 /M
Output$14.2 /M
Cache read$0.284 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

Gemini 4 Carbon
Kimi K3
Input
$2 /M
$2.84 /M
Output
$10 /M
$14.2 /M
Cache read
$0.1 /M
$0.284 /M
Context length
1,048,576
1,048,576
Max output
65,536
1,048,576
Time to First Token
7.0 s
0.6 s
Throughput
58.0 tok/s
73.1 tok/s
Modalities
textimagevideoaudiopdf
textimagevideo
Supported Parameters
thinkingfunction callingstructured outputs
API Formats
Released
November 11, 2026
July 16, 2026

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.

gemini-4-carbonkimi-k3

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

gemini-4-carbonkimi-k3

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
gemini-4-carbonkimi-k3
14401480152015601600
Overall
14871526
Coding
15371567
Math
15031503
Hard prompts
15151546
Instruction following
14881525
Multi-turn
15011564
Creative writing
14591515
Longer query
15001537
Chinese
15401585
English
14931524
WebDev Arena
gemini-4-carbonkimi-k3
15601640172018001880
Overall
16581768
React
16721792
HTML
16411770
Gaming
17041857
Simulations
16851862
Data analytics
15821666

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.

Gemini 4 Carbon
$270 /mo
Kimi K3
$383 /mo

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

FAQ

Which is cheaper: Gemini 4 Carbon, Kimi K3?

Gemini 4 Carbon: $10/M output tokens; Kimi K3: $14.2/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Gemini 4 Carbon: 1567; Kimi K3: 1537 (LMArena coding leaderboard).

Which responds faster?

Kimi K3: 0.6s 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?

Gemini 4 Carbon accepts 1,048,576 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 65,536 tokens on Gemini 4 Carbon and 1,048,576 tokens on Kimi K3.

Which one generates tokens faster?

Kimi K3 at 73.1 tok/s and Gemini 4 Carbon at 58.0 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Gemini 4 Carbon accepts text, image, video, audio and PDF input; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.

Can I call Gemini 4 Carbon 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.