Skip to content
NewTry RouterPlus with free creditsTry playground →
  • 1.05MContext
  • 524KMax output
  • $1.50/ $10.00From, per 1M in / out
  • 6Providers
Providers
  • Morph
  • DeepInfra
  • Nebius
  • Novita AI
  • Inference.net
  • Sail Research

Pricing

ProviderInput / 1MCached / 1MOutput / 1M
MorphDefault$2.50$0.29$14.00
DeepInfra$2.85$0.285$14.25
Nebius$3.00$0.30$15.00
Novita AI$3.00$0.30$15.00
Inference.net$3.00$0.30$15.00
Sail ResearchLowest$1.50$0.20$10.00

USD, as of October 27, 2026. Live prices

Cost

WorkloadMorphSail Research
1,000 chat replies2K in, 500 out each$12.00$8.00
1,000 agent tasks50K in, 5K out each$195.00$125.00
Monthly batch job500M in, 50M out$1,950.00$1,250.00

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",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

FAQ

How much does the Kimi K3 API cost?

On RouterPlus, routing for Kimi K3 starts at Morph: $2.50 per million input tokens and $14.00 per million output tokens. The lowest listed prices are at Sail Research: $1.50 input and $10.00 output. Name a provider with provider.only and you pay its price. Prices as of October 27, 2026.

Which providers serve Kimi K3?

6 providers serve Kimi K3 on RouterPlus: Morph, DeepInfra, Nebius, Novita AI, Inference.net and Sail Research. By default the router tries them in routing order and fails over before the first byte, never mid-answer.

What is the Kimi K3 model ID?

Use "moonshotai/kimi-k3" 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 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 open weights?

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

Do any Kimi K3 providers retain prompts?

5 of 6 providers list no prompt retention (DeepInfra, Nebius, Novita AI, Inference.net and Sail Research). Morph may retain prompts. Pin the providers you accept with a routing policy.

Can I reserve capacity for Kimi K3?

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

Need Kimi K3 at volume?