Nano GPT logo
NanoGPT
Provider logo

Kimi K3 TEE

TEE/kimi-k3
BackTry Model
Provider logo

Kimi K3 TEE

TEE/kimi-k3
BackTry Model

Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image understanding. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

Added Jul 31, 2026

Model weights

Context Window

1.0M

Max Output

1.0M

Input Price (Auto)

$3.15/1M

Output Price (Auto)

$15.75/1M

Cache Read (Auto)

$1.57/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

59.7

Better than 99% of models compared

Coding Index

76.2

Better than 95% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

93.5%

Better than 99% of models compared

HLE

Humanity's Last Exam

46.9%

Better than 98% of models compared

AA-LCR

Long context reasoning evaluation

82.7%

Better than 99% of models compared

Coding

SciCode

Python programming for scientific computing

58.7%

Better than 99% of models compared

Last updated Aug 16, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Kimi K3 TEE with similar models from the same provider or model family.

Kimi K2.7 Code TEE

TEE/kimi-k2.7-code

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode while running inside a Trusted Execution Environment (TEE) with attestation support.

Kimi K2.6 TEE

TEE/kimi-k2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model designed for long-horizon coding and agentic orchestration. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

Kimi K3

moonshotai/kimi-k3

Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image/video understanding.

Kimi K2.7 Code High-Speed

moonshotai/kimi-k2.7-code-highspeed

Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.

Kimi K2.7 Code

moonshotai/kimi-k2.7-code

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode; instant/non-thinking mode is not supported.

Kimi Latest

moonshotai/kimi-latest

Compatibility alias that routes to the newest Kimi model. Currently routes to Kimi K3.