Kimi-K2.6 (TEE)
Moonshot AI
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
- Tool calling: yes
- Image input: yes
Released
Apr 2026Modalities
Text · Tool calling · Image inputBest price on SayGM
-56.7%In
Cached
Out
per Mtok*
SayGM vs. list price
SayGM's best available rate for kimi-k2.6-tee next to the published list price — 56.7% off.
| Dimension | SayGM price | List price |
|---|---|---|
| Input | $0.285516per Mtok | $0.66 |
| Output | $1.5141per Mtok | $3.50 |
| Cache read | $0.142758per Mtok | $0.33 |
Recent effective price
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.46
$0.66Cached input
$0.28
$0.33Output
$2.26
$3.50How the effective price is calculated
Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 166 windows: 1,053 requests and 2,014,694 input-side tokens. Most recent window closed 2026-08-26 14:17 UTC.
Who's serving this model
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 56.7% off | $0.29 | $1.51 |
| Provider 2 | 4.2% off | $0.63 | $3.35 |
| Provider 3 | 4.2% off | $0.63 | $3.35 |
Performance
Measured on the requests SayGM routed to this model.
- Throughput
- 47.9 tok/sover 202 requests
- Time to first token
- 3.1 sover 202 requests
- Request success rate
- 100.0% over 102 requests
Benchmarks
Fixed-seed suites SayGM runs against this model.
Frequently asked questions
How much does kimi-k2.6-tee cost on SayGM?
The best available rate for kimi-k2.6-tee on SayGM right now is $0.29 per million input tokens and $1.51 per million output tokens.
How much cheaper is SayGM than list price?
SayGM's best available rate for kimi-k2.6-tee is 56.7% off list price.
Is kimi-k2.6-tee OpenAI-compatible on SayGM?
Yes. kimi-k2.6-tee is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.