Kimi K3.1 Pro API

Moonshot's Kimi K3.1 Pro, through an OpenAI-compatible API. 5 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send kimi-k3.1-pro as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: kimi-k3.1-pro
Maker: Moonshot
Context window: 1M tokens
Input price: $1.750 to $4.000 per million tokens
Output price: $8.899 to $20.000 per million tokens
Providers: 5 independent providers
Regions: asia, global, us, us-central, us-west

Providers

DreamcatcherAI: us-central, $1.790 input and $8.899 output per million tokens, $0.180 cache read per million tokens, 1M tokens of context
engy: asia, $1.790 input and $8.900 output per million tokens, $0.180 cache read per million tokens, 1M tokens of context
akash: us-west, $1.750 input and $10.000 output per million tokens, $0.180 cache read per million tokens, 1M tokens of context
EmpirioLabs AI: global, $2.000 input and $10.000 output per million tokens, $0.184 cache read per million tokens, 1M tokens of context
Pera: us, $4.000 input and $20.000 output per million tokens, $4.000 cache read per million tokens, $0.02 fee for each request, 1M tokens of context

Scores

Intelligence: 46.5, #5 of 41
HLE: 52.5, #7 of 273
AA-LCR: 86.3, #3 of 237
SciCode: 60.8, #5 of 123
SimpleQA Verified: 62.2, #16 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3.1-pro",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Kimi K3.1 Pro?: Kimi K3.1 Pro is a model from Moonshot.
How much does Kimi K3.1 Pro cost?: Offers now ask $1.750 to $4.000 per million input tokens and $8.899 to $20.000 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Kimi K3.1 Pro?: The largest offer takes 1,048,576 input tokens. One job can generate up to 1,048,576 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Kimi K3.1 Pro do?: Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.
What inputs and outputs does Kimi K3.1 Pro support?: Text · Images → Text.
Which providers serve Kimi K3.1 Pro?: 5 independent providers quote it now, with 5 offers. The table above ranks them by the cost of a typical job.
How do I call Kimi K3.1 Pro?: Send "kimi-k3.1-pro" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Kimi K3.1 Pro listed?: The exchange first listed it on 10/28/2026. This is not its release date.