← All posts · News
Kimi K3.1 Pro now on RouterPlus from 5 providers at $2/$10
Highspeed joins too, on Novita AI at $4/$20.
Kimi K3.1 Pro, Moonshot AI's open-weight flagship, joined the RouterPlus catalog on November 5, 2026, served by 5 providers. Its faster variant, Kimi K3.1 Pro Highspeed, joined on one. Moonshot launched both on its own API on October 23 and published the K3.1 Pro weights on Hugging Face on November 4.
What changed
- New RouterPlus model IDs:
moonshotai/kimi-k3.1-proandmoonshotai/kimi-k3.1-pro-highspeed. - Kimi K3.1 Pro is served by Doubleword, Inference.net, Nebius, Novita AI and Wafer. All 5 charge the same: $2.00 input, $0.20 cached input and $10.00 output per million tokens.
- Highspeed is served by Novita AI at $4.00 input, $0.20 cached input and $20.00 output. Moonshot says Highspeed runs at 2 to 3 times the speed of K3.1 Pro.
- The catalog lists a 1,048,576-token context window and up to 524,288 output tokens for both models.
Pricing on RouterPlus
RouterPlus catalog, November 5, 2026, per million tokens:
| Model | Provider | Input | Cached input | Output |
|---|---|---|---|---|
| Kimi K3.1 Pro | Doubleword | $2.00 | $0.20 | $10.00 |
| Kimi K3.1 Pro | Inference.net | $2.00 | $0.20 | $10.00 |
| Kimi K3.1 Pro | Nebius | $2.00 | $0.20 | $10.00 |
| Kimi K3.1 Pro | Novita AI | $2.00 | $0.20 | $10.00 |
| Kimi K3.1 Pro | Wafer | $2.00 | $0.20 | $10.00 |
| K3.1 Pro Highspeed | Novita AI | $4.00 | $0.20 | $20.00 |
Moonshot's own API prices are in our launch post. Licence terms for the weights are in our open weights post.
What to do
Moving from Kimi K3 is a model ID swap on the same endpoint:
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"}]}'Every provider and price: Kimi K3.1 Pro API pricing and Kimi K3.1 Pro Highspeed. All Moonshot AI models.