Impulse
Models/Kimi-K2-Instruct
Compare

Kimi-K2-InstructActive · Cloud

WandB Inference · Released · Modified MIT License

Wandb chat model.

Context
128K
Max output
128K
Input
$0.60
Output
$2.50
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Details

ProviderWandB Inference
Released
LicenseModified MIT License
InputText
OutputText
Throughput-
Availability-

Related models

MiniMax-M2.5WandB Inference197K$0.30Kimi-K2.5WandB Inference262K$0.60gpt-oss-120bWandB Inference131K$15000.00