Back to Models Overview

Compare Models

Click on a column header to sort and find the best model for your use case.

Model
Provider
Context Window
Input Pricing
Output Pricing
Horton T1
Horton
Up to 256k tokens (expandable via streaming memory)Pricing not yet availableWill be announced upon release
Horton T1 mini
Horton
16k tokens (mobile) to 64k (desktop)Pricing not yet availableWill be announced upon release
Gemini 2.5 Pro
Google
≈1,048,576 input / 65,536 output tokens$1.25 / 1M tokens (≤200k context), $2.50 > 200k$10.00 / 1M tokens (≤200k), $15.00 > 200k
Gemini 2.0 Flash
Google
1,000,000 tokens$0.10 / 1M tokens$0.40 / 1M tokens
GPT-5
OpenAI
Not published$1.25 / 1M tokens$10.00 / 1M tokens
GPT-5 mini
OpenAI
Not published$0.25 / 1M tokens$2.00 / 1M tokens
Claude Opus 4.1
Anthropic
Not published$15.00 / 1M tokens$75.00 / 1M tokens
Claude Sonnet 4.5
Anthropic
Up to 1,000,000 tokens (Sonnet 4 series)$3.00 / 1M tokens$15.00 / 1M tokens
Grok 4
xAI
256,000 tokens$3.00 / 1M tokens$15.00 / 1M tokens