uttapen

MoonshotAI Kimi Latest vs Kimi K3

Both sit behind the same key and the same code on uttapen — the only thing that changes is the model string, so you can run each of them against your own workload without touching anything else. On cost, MoonshotAI Kimi Latest comes out about 1.2× cheaper.

FeatureMoonshotAI Kimi LatestKimi K3
ProviderMoonshot (Kimi)Moonshot (Kimi)
Model id~moonshotai/kimi-latestmoonshotai/kimi-k3
Context1,048,576 tokens1,048,576 tokens
Max output943,718 tokens943,718 tokens
Input / 1M tokens739,819 toman870,375 toman
Output / 1M tokens3,699,094 toman4,351,875 toman
≈ one 1,000-word request5,771 toman6,789 toman
Input caching74,272 toman / 1M87,038 toman / 1M
Image inputYesYes
File inputNoNo
Tool callingYesYes
JSON outputYesYes
Reasoning modeYesYes

Which one for what?

MoonshotAI Kimi Latest

  • Multi-step problems, maths, and tracking down a bug
  • Whole documents or a codebase in a single request
  • Reading screenshots, invoices, and scanned forms
  • Agents that call your own APIs and database
5,771 toman per 1,000 words · Model page

Kimi K3

  • Multi-step problems, maths, and tracking down a bug
  • Whole documents or a codebase in a single request
  • Reading screenshots, invoices, and scanned forms
  • Agents that call your own APIs and database
6,789 toman per 1,000 words · Model page

Run both with the same code

Swap the model value between the two ids and send the same request twice; what each answer cost comes back in the X-Uttapen-Cost-Toman header.

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "~moonshotai/kimi-latest",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

model = "moonshotai/kimi-k3"

More comparisons: all pairs · model rankings · full catalogue

base_url = https://api.uttapen.ir/v1