DeepSeek V4 Pro 0423 vs Kimi K3

Practical read: DeepSeek V4 Pro 0423 costs about a third as much. Kimi K3 starts answering sooner and generates faster. One API key runs both.

No card required. Start with 1 million free tokens.

Side by side:

DeepSeek V4 Pro 0423 compared with MoonshotAI: Kimi K3
Attribute	DeepSeek V4 Pro 0423 `deepseek/deepseek-v4-pro-0423`	Kimi K3 `moonshotai/kimi-k3`
Price, 1M in + out	$4.11 DeepInfra, cheapest route	$11.97 Chutes, cheapest route
Best for	Low cost	Speed
Input / output, 1M	$1.37 / $2.74	$1.95 / $10.02
Cached input	$0.1055/1M to $0.34815/1M	$0.1688/1M to $0.910887/1M
Context window	1.05M 1,048,576 tokens	1.05M 1,048,576 tokens
First token, p50	1.8 s via SiliconFlow	0.82 s via Telnyx
Throughput	154 tok/s via DeepInfra	255 tok/s via Wafer
AI IQ	Unrated	IQ 127 #22 on AI IQ
Provider routes	3 with failover	26 with failover
Privacy	Varies by provider	Confidential E2EE and zero retention route
Recent route uptime range	100.00%	66.67% to 100.00%
Publisher	DeepSeek	Kimi
Modes	chat	chat
More detail	Overview Pricing Providers	Overview Pricing Providers

Price adds one million input and one million output tokens on the cheapest route. Prices and speed change: see the monthly reports and run a small eval before you choose a default.

Test both with your agent

Paste this into Claude Code, Cursor or any coding agent.

Compare DeepSeek V4 Pro 0423 and Kimi K3 in this project through TrustedRouter.

1. Read https://trustedrouter.com/docs/llms.txt
2. Point the OpenAI-compatible client at
   https://api.trustedrouter.com/v1 and read the key from
   TRUSTEDROUTER_API_KEY.
3. Run our eval prompts on deepseek/deepseek-v4-pro-0423, then on moonshotai/kimi-k3.
4. Show me cost, latency and quality side by side before changing the default.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
for model in ("deepseek/deepseek-v4-pro-0423", "moonshotai/kimi-k3"):
    response = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": "What is the capital of France?"}],
    )
    print(model, response.choices[0].message.content)

for model in deepseek/deepseek-v4-pro-0423 moonshotai/kimi-k3; do
  curl https://api.trustedrouter.com/v1/chat/completions \
    -H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{\"model\": \"$model\", \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}]}"
done

Your agent will need an API key.

Questions

Which should I use, DeepSeek V4 Pro 0423 or MoonshotAI: Kimi K3?

DeepSeek V4 Pro 0423 has the lower published input-plus-output rate. MoonshotAI: Kimi K3 has more Credits provider routes and the lower measured p50 time to first token. Their context windows are the same size.

Is DeepSeek V4 Pro 0423 or MoonshotAI: Kimi K3 cheaper?

The current cheapest TrustedRouter route is $4.1145/1M for DeepSeek V4 Pro 0423 and $11.97425/1M for MoonshotAI: Kimi K3. The comparison uses current catalog prices and updates as provider pricing changes.

Is DeepSeek V4 Pro 0423 or MoonshotAI: Kimi K3 faster?

Current measured p50 time to first token is 1799 ms for DeepSeek V4 Pro 0423 and 823 ms for MoonshotAI: Kimi K3. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test DeepSeek V4 Pro 0423 and MoonshotAI: Kimi K3 with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between deepseek/deepseek-v4-pro-0423 and moonshotai/kimi-k3. This makes side-by-side evals possible without maintaining two provider integrations.

More comparisons

All comparisons

Try DeepSeek V4 Pro 0423 and Kimi K3 with one key.

TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.

No card required. Start with 1 million free tokens.