Pricing
| Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|
| Nebius | $0.95 | $0.16 | $4.00 |
| Inference.net | $1.25 | $0.21 | $5.30 |
| Sail Research | $1.00 | $0.20 | $4.00 |
USD, as of October 27, 2026. Live prices
Kimi K2.6 API
- 262KContext
- 262KMax output
- $0.95/ $4.00From, per 1M in / out
- 3Providers
Providers
Cost
| Workload | Nebius |
|---|---|
| 1,000 chat replies2K in, 500 out each | $3.90 |
| 1,000 agent tasks50K in, 5K out each | $67.50 |
| Monthly batch job500M in, 50M out | $675.00 |
Quickstart
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2.6",
"messages": [{ "role": "user", "content": "Hello" }]
}'FAQ
How much does the Kimi K2.6 API cost?
On RouterPlus, Kimi K2.6 costs $0.95 per million input tokens and $4.00 per million output tokens at Nebius, the lowest listed prices and the provider where routing starts. Prices as of October 27, 2026.
Which providers serve Kimi K2.6?
3 providers serve Kimi K2.6 on RouterPlus: Nebius, 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 K2.6 model ID?
Use "moonshotai/kimi-k2.6" 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 K2.6 context window?
262K tokens of context and up to 262K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.
Is Kimi K2.6 open weights?
Yes. Moonshot AI publishes Kimi K2.6 as an open-weight model, which is why several independent providers can host it.
Do any Kimi K2.6 providers retain prompts?
None of the 3 providers serving Kimi K2.6 on RouterPlus list prompt retention.
Can I reserve capacity for Kimi K2.6?
Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.