AIHubMixAIHubMix
← Models

Kimi K2 0711 vs Kimi K3

Output tokens cost $2.16 per million on Kimi K2 0711 and $15.00 per million on Kimi K3. Input tokens cost $0.54 per million on Kimi K2 0711 and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.54 per million on Kimi K2 0711 and $0.30 per million on Kimi K3. Context lengths are 131,000 tokens on Kimi K2 0711 and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 0.8s on Kimi K2 0711 and 0.9s on Kimi K3. Measured output throughput is 50.2 tok/s on Kimi K2 0711 and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard Kimi K2 0711 scores 1467 and Kimi K3 scores 1531.

Moonshot AIKimi K2 0711Moonshot AIKimi K3
+ Add model · 2/4
Moonshot AI logo
Kimi K2 0711
Moonshot AI · text → text

Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent capabilities, featuring a total of 1 trillion parameters and activating 32 billion parameters. In benchmark performance tests across major categories such as general knowledge reasoning, programming, mathematics, and agents, the K2 model outperforms other mainstream open-source models. The Kimi-K2 model supports a context length of 128k tokens. It does not support visual capabilities.

Input$0.54 /M
Output$2.16 /M
Details
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
Details

Pricing & Specifications

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

Kimi K2 0711
Kimi K3
Input /M
$0.54
$3.00
Output /M
$2.16
$15.00
Cache read /M
$0.54
$0.30
Context length
131,000
1,048,576
Max output
131,000
1,048,576
Time to First Token
0.8 s
0.9 s
Throughput
50.2 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.

kimi-k2-0711kimi-k3

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

kimi-k2-0711kimi-k3

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
kimi-k2-0711kimi-k3
1360142014801540
Overall
14181486
Coding
14671531
Math
14161416
Hard prompts
14371505
Instruction following
13901479
Multi-turn
14041499
Creative writing
13821470
Longer query
14031502
Chinese
14541527
English
14231491

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 K2 0711
$64.80 /mo
Kimi K3
$405 /mo

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

FAQ

Which is cheaper: Kimi K2 0711, Kimi K3?

Kimi K2 0711: $2.16/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; Kimi K2 0711: 1467 (LMArena coding leaderboard).

Which responds faster?

Kimi K2 0711: 0.8s 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 K2 0711 accepts 131,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 131,000 tokens on Kimi K2 0711 and 1,048,576 tokens on Kimi K3.

Which one generates tokens faster?

Kimi K3 at 73.1 tok/s and Kimi K2 0711 at 50.2 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 K2 0711 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 Kimi K2 0711 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.

kimi-k3vsqwen3.8-max-previewclaude-opus-5vsgpt-5.6-lunaclaude-opus-5vsclaude-sonnet-5gemini-3.1-pro-previewvsgpt-5.5glm-5.2vskimi-k3gemini-3.6-flashvsqwen3.8-maxdeepseek-v4-flashvsglm-5.2claude-opus-5vsgrok-4.5
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect