Kimi K2.5 API
About
Build advanced reasoning agents with Kimi K2.5, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.60/1M input and $3.00/1M output tokens, native tool calling support, open weights architecture. Access Kimi K2.5 via the Fireworks AI API with up to 256K output tokens.
Capabilities
Input Modalities
textimagevideo
Output Modalities
text
Limits
Context Window
256K
Tokens
Input Limit
256K
Tokens
Max Output
256K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.60
Output
$3.00
Caching (per 1M tokens)
Read
$0.10
Frequently Asked Questions
Kimi K2.5 by Fireworks AI costs $0.60 per 1M input tokens and $3.00 per 1M output tokens. Cached reads cost $0.10 per 1M tokens.
Model Details
ID
accounts/fireworks/models/kimi-k2p5
Provider
Fireworks AIFamily
kimi-thinking
Release Date
Jan 27, 2026
Knowledge Cutoff
Jan 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
FIREWORKS_API_KEY
API Base URL
https://api.fireworks.ai/inference/v1/