Back to all models

Kimi K2 Thinking

Kimi K2 with extended thinking capabilities.

kimi-k2-thinking
STABLEScheduled for DeactivationGet StartedView uptime
262,144 context
Starting at $0.57/M input tokens
Starting at $2.29/M output tokens
Streaming
Tools
Reasoning
JSON Output

Select Provider

All Providers for Kimi K2 Thinking

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Moonshot AI
Context: 262.1k
Deactivated since Jun 28, 2026
Input
$0.6
/M tokens
Cached
$0.15
/M tokens
Output
$2.5
/M tokens
Get Started
ByteDance
Context: 256k
Deactivated since Jun 28, 2026
Input
$0.6
/M tokens
Cached
$0.12
/M tokens
Output
$2.5
/M tokens
Get Started
Alibaba Cloud
Context: 262.1k
Deactivated since Jul 8, 2026
Input
$0.574
/M tokens
Cached
—
/M tokens
Output
$2.294
/M tokens
Get Started
Vertex AI (OpenAI-compatible)
Context: 262.1k
Deactivating on Oct 21, 2026
Input
$0.6
/M tokens
Cached
$0.06
/M tokens
Output
$2.5
/M tokens
Get Started