Pricing
What a request costs — the Enso tiers, per-token billing for every other model, and the per-call rates for tools, images and audio.
After this page you can work out what a request will cost before you send it, and pick the tier that makes that number worth paying.
You are billed for what you use — tokens for a chat model, calls for a tool, images for an image model. There is no seat licence and no minimum: an account that sends nothing is charged nothing.
Every rate below is per million tokens unless the table says otherwise, in US dollars.
The Enso tiers
Enso is Hanzo's own family. Each paid tier runs a chain of frontier
models under one id and one price, and a call bills that price whichever
model answered it. enso-auto, the default, picks a tier per request and
bills at the tier that answers.
| Model | Input | Output |
|---|---|---|
enso-flash | $0.33 | $1.65 |
enso-pro | $3.30 | $16.50 |
enso-max | $4.30 | $21.50 |
enso-ultra | $5.236 | $26.18 |
Fast mode, "fast": true in the body or the header X-Fast: 1, bills 2x
on enso-auto and enso-flash, 3x on enso-pro and enso-max, and 4x on
enso-ultra, always from prepaid balance.
Cache read and write rates, the models behind each tier, and a worked cost for an agent turn: Enso.
Every other model
Alongside the Enso and Zen families the gateway carries models from outside labs, on the same key and the same endpoint. Each is billed at its own published rate.
Those rates move as providers change theirs, so they are not reprinted here. The catalogue at Models fetches them in your browser as you read, which means it is current without waiting for a docs deploy — read the price there, next to the model id you are about to paste.
Tools
Tool calls are billed by their own unit, not by tokens:
| Tool | Unit | Price |
|---|---|---|
| Web Search | per call | $0.002 |
| Code Interpreter | per session minute | $0.03 |
| File Storage | per GB/month | $0.20 |
| Image Generation | per image | $0.04 |
| Speech-to-Text | per minute | $0.006 |
| Text-to-Speech | per 1M characters | $15.00 |
| Web Fetch | per call | $0.001 |
What you are actually charged
A token is roughly three quarters of a word, so a 2,000-token prompt is about three pages. Divide the rate by a million and multiply:
cost = (input_tokens x input_rate + output_tokens x output_rate) / 1_000_000You never have to trust that arithmetic. Every response to
/v1/chat/completions carries a usage object counting exactly what was
billed:
{
"usage": {
"prompt_tokens": 2000,
"completion_tokens": 500,
"total_tokens": 2500
}
}Where a model publishes a cache-read rate, tokens served from cache are
billed at that lower rate instead of the input rate — the catalogue shows it
per model as cacheRead.
Read the rates programmatically
The page you are reading is generated from this endpoint, so it can tell you nothing the endpoint will not:
curl -s https://api.hanzo.ai/v1/models | jq '.data[] | select(.id | test("^enso-")) | {id, pricing}'It needs no key. /v1/pricing returns the Hanzo family, the third-party
rates, the tool table, and the provider breakdown in one document;
/v1/models returns the same rates alongside the model ids you pass as
model.
Next
Per-token rates read from /v1/models. Everything else captured from /v1/pricing on 2026-11-21.