Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

Kimi K3.1 Pro API

Open in consoleI need inference
  • 1.05MContext
  • 524KMax output
  • $2.00/ $10.00From, per 1M in / out
  • 5Providers
Providers
  • Nebius
  • Novita AI
  • Inference.net
  • Doubleword
  • Wafer

Pricing

ProviderInput / 1MCached / 1MOutput / 1M
NebiusDefaultLowest$2.00$0.20$10.00
Novita AI$2.00$0.20$10.00
Inference.net$2.00$0.20$10.00
Doubleword$2.00$0.20$10.00
Wafer$2.00$0.20$10.00

USD, as of November 5, 2026. Live prices

Cost

WorkloadNebius
1,000 chat replies2K in, 500 out each$9.00
1,000 agent tasks50K in, 5K out each$150.00
Monthly batch job500M in, 50M out$1,500.00

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k3.1-pro",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

FAQ

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

On RouterPlus, Kimi K3.1 Pro costs $2.00 per million input tokens and $10.00 per million output tokens at Nebius, the lowest listed prices and the provider where routing starts. Prices as of November 5, 2026.

Which providers serve Kimi K3.1 Pro?

5 providers serve Kimi K3.1 Pro on RouterPlus: Nebius, Novita AI, Inference.net, Doubleword and Wafer. By default the router tries them in routing order and fails over before the first byte, never mid-answer.

What is the Kimi K3.1 Pro model ID?

Use "moonshotai/kimi-k3.1-pro" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.

What is the Kimi K3.1 Pro context window?

1.05M tokens of context and up to 524K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.

Is Kimi K3.1 Pro open weights?

Yes. Moonshot AI publishes Kimi K3.1 Pro as an open-weight model, which is why several independent providers can host it.

Do any Kimi K3.1 Pro providers retain prompts?

4 of 5 providers list no prompt retention (Nebius, Novita AI, Inference.net and Wafer). Doubleword may retain prompts. Pin the providers you accept with a routing policy.

Can I reserve capacity for Kimi K3.1 Pro?

Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.

More Kimi

All Kimi modelsAll models

Need Kimi K3.1 Pro at volume?

Open in consoleI need inference