AI Model APIs
AI Model APIsProviders
AI Model APIs

The complete platform for comparing AI models. Find pricing, capabilities, and the perfect model for your use case.

contact@aimodelapis.com

Resources

  • AI Models APIs
  • Providers

About

  • About
  • Contact
  • Privacy Policy
  • Terms of Service

© 2026 AI Model APIs. All rights reserved.

Back to Models
Poe

Kimi-K2.5 API

Poe
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. Access Kimi-K2.5 via the Poe API with up to 262K output tokens.

Capabilities

Input Modalities

textimagevideo

Output Modalities

text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsClosed
Temperature
Adjustable
Attachment
Supported
Limits
Context Window
128K

Tokens

Input Limit
128K

Tokens

Max Output
262K

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 Poe 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
novita/kimi-k2.5
Provider
Poe
Family
Release Date
Jan 27, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
POE_API_KEY
API Base URL
https://api.poe.com/v1
Documentation