whichllm — Browse and compare AI model specs and pricing

Nebius Token Factory

Kimi-K2.5-fast model ID, context window & pricing

kimi-k2

Quick facts

Model ID moonshotai/Kimi-K2.5-fast
Source Nebius Token Factory
Context Window 256000
Pricing $0.50 input / $2.50 output per 1M tokens
Capabilities tool calling, reasoning, structured output, temperature control, open weights

Model overview

Kimi-K2.5-fast is an AI model from Nebius Token Factory with 256000 token context window and text, image input support.

Published pricing is $0.50 input and $2.50 output per 1M tokens.

  • Workloads that use text, image inputs with text outputs.
  • Agent and tool workflows that need function calling.
  • Reasoning-heavy prompts where stepwise problem solving matters.
Model ID moonshotai/Kimi-K2.5-fast
Provider Nebius Token Factory
Family kimi-k2
Status deprecated
Knowledge Cutoff 2025-06
Release Date 2025-12-15
Input Modalities text, image
Output Modalities text
Context Window 256000
Input Limit 256000
Output Limit 8192
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.50
Output Cost / 1M tokens $2.50
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.05
Cache Write Cost / 1M tokens $0.62