MoonshotAI: Kimi K3

Moonshot AI

moonshot/kimi-k3

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Context

1.048576M

Input /1M

$3.00

Output /1M

$15.00

Latency (TTFT)

1,806ms

Pricing

Per 1M tokens, in USD

Input$3.00

Output$15.00

Cache read$0.30

Specs

text inimage invideo intext out

TokenizerOther

Max output tokens943,718

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$3.00

Cheaper than 11% of routable models

Output$15.00

Cheaper than 8% of routable models

Benchmarks

Intelligence43.8

Coding76.2

Agentic50.6

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshot/kimi-k3",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

MoonshotAI: Kimi K3

Moonshot AI

moonshot/kimi-k3

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Context

1.048576M

Input /1M

$3.00

Output /1M

$15.00

Latency (TTFT)

1,806ms

Pricing

Per 1M tokens, in USD

Input$3.00

Output$15.00

Cache read$0.30

Specs

text inimage invideo intext out

TokenizerOther

Max output tokens943,718

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$3.00

Cheaper than 11% of routable models

Output$15.00

Cheaper than 8% of routable models

Benchmarks

Intelligence43.8

Coding76.2

Agentic50.6

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshot/kimi-k3",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'