Kimi K3 TEE by Chutes | AI model information

$10 off the fastest Kimi K3 and GLM 5.2$10 off the fastest Kimi K3 and GLM 5.2

Discuss

Model details

Kimi K3 TEE

Chutesmoonshotai/Kimi-K3-TEEkimi-k3

Open provider page Provider docs

Quick Info

Provider: Chutes
Model key: moonshotai/Kimi-K3-TEE
Release date: Jul 29, 2026

Cost

Input token cost: $3.00
Output token cost: $15.00

Limits

Output tokens: 65,535 tokens
Context window

Latest news about Kimi K3 TEE

Videos about Kimi K3 TEE

Recent tweets and retweets from Chutes

Aug 4, 2026, 6:03 PMUTC

Week 12. A shipping week for the confidential-compute stack: → Next TEE release is staged and in testing: mutual-TLS on attestation, hardware-attested registry access, and measurements third parties can verify themselves → Every GPU node on Chutes is now TEE-verified. The…

Aug 4, 2026, 6:02 PMUTC

Article Last Week in Chutes | July 29 to August 4, 2026 Last Week in Chutes July 29 to August 4, 2026 Week twelve. A shipping week for the confidential-compute stack. The next TEE release is staged and in testing, the legacy non-TEE verification path is on

Aug 3, 2026, 7:00 PMUTC

Recurrent attention would not sync. Jon Durbin tried the existing decentralized algorithms, the whole DiLoco family included, and none of them translate. So he built a new sync method into Parallax, exact and fully non-blocking, within 0.6% of the centralized DDP baseline at…

Aug 3, 2026, 1:30 PMUTC

165,335 tokens per second. That is Parallax pre-training a 5B test model on eight consumer RTX 5090s. Optimized DDP training on eight RTX Pro 6000s managed 147,708. Hardware that costs roughly 3x more. Parallax won even on the cheaper hardware.

Aug 3, 2026, 1:30 PMUTC

Numbers are from Jon Durbin's run last week: nitter.net/jon_durbin/status/2082… Parallax is built in the open at chutes.ai