Pricing
| Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|
| Inference.net | $4.50 | $0.45 | $22.50 |
USD, as of October 27, 2026. Live prices
Kimi K3 Fast API
- 1.05MContext
- 1.05MMax output
- $4.50/ $22.50From, per 1M in / out
- 1Provider
Providers
Cost
| Workload | Inference.net |
|---|---|
| 1,000 chat replies2K in, 500 out each | $20.25 |
| 1,000 agent tasks50K in, 5K out each | $337.50 |
| Monthly batch job500M in, 50M out | $3,375.00 |
Quickstart
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k3-fast",
"messages": [{ "role": "user", "content": "Hello" }]
}'FAQ
How much does the Kimi K3 Fast API cost?
On RouterPlus, Kimi K3 Fast costs $4.50 per million input tokens and $22.50 per million output tokens at Inference.net, the lowest listed prices and the provider where routing starts. Prices as of October 27, 2026.
Which providers serve Kimi K3 Fast?
Inference.net serves Kimi K3 Fast on RouterPlus today.
What is the Kimi K3 Fast model ID?
Use "moonshotai/kimi-k3-fast" 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 Fast context window?
1.05M tokens of context and up to 1.05M output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.
Is Kimi K3 Fast open weights?
Yes. Moonshot AI publishes Kimi K3 Fast as an open-weight model, which is why several independent providers can host it.
Do any Kimi K3 Fast providers retain prompts?
None of the 1 providers serving Kimi K3 Fast on RouterPlus list prompt retention.
Can I reserve capacity for Kimi K3 Fast?
Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.