Last refreshed 2026-10-30. Next refresh: weekly.
Why use Ampersand Tutor on humans& Agents API?
humans& Agents API offers Ampersand Tutor with pay-as-you-go pricing at $1.00/1M input tokens. humans& first-party Agents API serving Ampersand.
Input / 1M
$1.00
Output / 1M
$5.20
Cache
read $0.20
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: ampersand-tutor-v0.1Model ID
ampersand-tutor-v0.1Request example
Curated snippets for this provider are not sourced yet. Use humans& Agents API documentation with model ID
ampersand-tutor-v0.1.Gotchas
- Use provider model ID "ampersand-tutor-v0.1", not the LLMReference slug "ampersand-tutor".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.00 |
| Output tokens | $5.20 |
Capabilities
Reasoning
About Ampersand Tutor
Ampersand Tutor (&Tutor) is humans&'s tutoring model, released October 30, 2026 through the Ampersand API as ampersand-tutor-v0.1. Built on GLM 5.3, it learns to teach by training against Persimmon, humans&'s large-scale model of how students learn, and aims to maximize a student's understanding rather than just give answers. It is a mixture-of-experts transformer (78 layers, 256 routed experts plus 1 shared, 8 active per token) served in NVFP4, with text input and output.
Get Started
Model Specs
Released2026-10-30
ArchitectureMixture of Experts