AIHubMixAIHubMix
← Models

ERNIE 5.0 Thinking Preview vs Kimi K3

Output tokens cost $3.29 per million on ERNIE 5.0 Thinking Preview and $15.00 per million on Kimi K3. Input tokens cost $0.82 per million on ERNIE 5.0 Thinking Preview and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.82 per million on ERNIE 5.0 Thinking Preview and $0.30 per million on Kimi K3. Context lengths are 183,000 tokens on ERNIE 5.0 Thinking Preview and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 6.5s on ERNIE 5.0 Thinking Preview and 0.9s on Kimi K3. Measured output throughput is 72.1 tok/s on ERNIE 5.0 Thinking Preview and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard ERNIE 5.0 Thinking Preview scores 1491 and Kimi K3 scores 1531.

BaiduERNIE 5.0 Thinking PreviewMoonshot AIKimi K3
+ Add model · 2/4
Baidu logo
ERNIE 5.0 Thinking Preview
Baidu · text → text

The new generation Wenxin model, Wenxin 5.0, is a native full-modal large model that adopts native full-modal unified modeling technology, jointly modeling text, images, audio, and video, possessing comprehensive full-modal capabilities. Wenxin 5.0's basic abilities are comprehensively upgraded, performing excellently on benchmark test sets, especially in multimodal understanding, instruction compliance, creative writing, factual accuracy, intelligent agent planning, and tool application.

Input$0.82 /M
Output$3.29 /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.

ERNIE 5.0 Thinking Preview
Kimi K3
Input /M
$0.82
$3.00
Output /M
$3.29
$15.00
Cache read /M
$0.82
$0.30
Context length
183,000
1,048,576
Max output
64,000
1,048,576
Time to First Token
6.5 s
0.9 s
Throughput
72.1 tok/s
73.1 tok/s
Modalities
text
textimagevideo
Supported Parameters
thinkingstructured outputsfunction calling
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.

ernie-5.0-thinking-previewkimi-k3

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

ernie-5.0-thinking-previewkimi-k3

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
ernie-5.0-thinking-previewkimi-k3
14001440148015201560
Overall
14471486
Coding
14911531
Math
14381438
Hard prompts
14651505
Instruction following
14271479
Multi-turn
14411499
Creative writing
14231470
Longer query
14401502
Chinese
14961527
English
14511491

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.

ERNIE 5.0 Thinking Preview
$98.64 /mo
Kimi K3
$405 /mo

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

FAQ

Which is cheaper: ERNIE 5.0 Thinking Preview, Kimi K3?

ERNIE 5.0 Thinking Preview: $3.29/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; ERNIE 5.0 Thinking Preview: 1491 (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?

ERNIE 5.0 Thinking Preview accepts 183,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 64,000 tokens on ERNIE 5.0 Thinking Preview and 1,048,576 tokens on Kimi K3.

Which one generates tokens faster?

Kimi K3 at 73.1 tok/s and ERNIE 5.0 Thinking Preview at 72.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

ERNIE 5.0 Thinking Preview accepts text input and supports thinking, structured outputs and function calling; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.

Can I call ERNIE 5.0 Thinking Preview 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