Moonshot AI · Text

Kimi K3.1 Pro API pricing

Moonshot AI’s Kimi K3.1 Pro through one prepaid, OpenAI-compatible key: $1.92 input, $10.04 output per 1M tokens, the provider’s list price with nothing added per request.

Model id kimi-k3-1-pro Add credit

Kimi K3.1 Pro price per 1M tokens

Input
$1.92
per 1M tokens
Cached input
$0.192
per 1M tokens, on a cache hit
Output
$10.04
per 1M tokens

Moonshot AI’s list price, in US dollars. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request.

What Kimi K3.1 Pro is good at

Moonshot's flagship. It always thinks, at low, high or max effort. 1M context, image input.

In short: flagship, always thinking, 1M context.

  • Tool calls
  • Image understanding
  • Reasoning effort
  • 1M context
  • Prompt caching

Text model, called at /v1/chat/completions. Listed under text generation, reasoning and vision.

Kimi K3.1 Pro context window and limits

Provider
Moonshot AI
Type
Text
Context window
1M tokens
Max output
1M tokens
Endpoint
/v1/chat/completions
Model id
kimi-k3-1-pro

What Kimi K3.1 Pro costs per request

Typical requests at the list rate, worked out once. Your own counts go in the calculator below.

What typical Kimi K3.1 Pro requests cost at the list price
RequestInputOf which cachedOutputPer requestPer 1,000
Short chat reply1,500—300$0.005892$5.89
Support bot, cached system prompt6,0005,000500$0.007901$7.90
Summarise a 100-page document60,000—1,500$0.1303$130.25
Agent step, long cached context200,000180,0002,000$0.0930$93.04

Token counts are examples; the rates are Moonshot AI’s list prices. Tokens.Pay adds nothing per request.

Kimi K3.1 Pro cost calculator

Set the size of a typical request. Prices are per token, so the estimate is exact for those counts.

The share of input the provider serves from its cache, billed at $0.192 per 1M.

Per request
$0.007133
Per 1,000 requests
$7.13
$25 of credit covers
3,504requests

Call Kimi K3.1 Pro with the OpenAI SDK

Base URL https://api.airuntime.dev/v1, your key as the bearer token, and model set to kimi-k3-1-pro.

curl

curl https://api.airuntime.dev/v1/chat/completions \
  -H "Authorization: Bearer $TOKENS_PAY_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3-1-pro",
    "messages": [{"role": "user", "content": "Say hello in five words."}]
  }'

Who processes Kimi K3.1 Pro requests

Your code calls AI Runtime directly. It forwards the request to the provider and keeps only the bill.

Processing and storage

Model provider
Moonshot AI, mainland China · data terms
Gateway
AI Runtime, AWS us-east-1

Not stored by Tokens.Pay or AI Runtime. Prompts and outputs exist in memory only while the request runs; we keep the billing record. The provider processes the request under its own terms. Zero data retention, exactly

Compare Kimi K3.1 Pro with similar models

All 16 models
Kimi K3.1 Pro compared with similar models
ModelProviderInput /1MCached /1MOutput /1MContext
Kimi K3.1 Pro (this page) Moonshot AI $1.92$0.192$10.041M
Kimi K3.1 Pro Highspeed Moonshot AI $3.84$0.192$20.081M
GPT-6.1 Sol OpenAI $2.00$0.10$10.001.05M
GPT-6.1 Terra OpenAI $1.00$0.05$5.001.05M
DeepSeek V4.1 Flash DeepSeek $0.15$0.003$0.601M
GPT-6 Luna OpenAI $0.10$0.01$0.501.05M

Kimi K3.1 Pro API questions

How much does the Kimi K3.1 Pro API cost?

$1.92 per 1M input tokens, $0.192 per 1M cached input tokens and $10.04 per 1M output tokens: Moonshot AI’s list price. Tokens.Pay adds nothing per request; a 5% fee (minimum $0.79) applies when you add credit.

What is the model id for Kimi K3.1 Pro?

Send model "kimi-k3-1-pro" to https://api.airuntime.dev/v1/chat/completions with your Tokens.Pay key as the bearer token. Any OpenAI-compatible SDK works.

What is the Kimi K3.1 Pro context window?

1M tokens, with up to 1M output tokens per request.

Does Tokens.Pay store my Kimi K3.1 Pro prompts?

No. AI Runtime, the gateway your key calls, keeps prompts and outputs in memory only while the request runs and stores just the billing record. The request is processed by Moonshot AI (mainland China), under the provider’s own API data terms.

Does Kimi K3.1 Pro support prompt caching?

Yes. Input tokens served from Moonshot AI’s cache are billed at $0.192 per 1M instead of $1.92. Your Dashboard shows your cache hit rate.

Add credit, then call Kimi K3.1 Pro.

From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.

Add credit