Point stale Enso tier lists at the Enso page

Chat, the glossary, the models index, the workspace sheet and the
coding guides named enso as a paid tier and enso-flash at a 262K
window, and none named enso-pro. Name enso-auto and the three paid
tiers, and link the Enso page for prices. The workspace sheet's
escalation and savings figures were computed on the old prices; they
go.

The Claude Code guide and settings example fill the Haiku, Sonnet and
Opus slots the way hanzo --claude --cloud does.

Claude-Session: https://claude.ai/code/session_01M8RoubcPN71KgJuZ8LdBUL
This commit is contained in:
2026-10-15 14:52:14 -07:00
parent bc7d42e2b9
commit ff736ace53
8 changed files with 19 additions and 20 deletions
@@ -29,8 +29,9 @@ endpoints:
apiKey: "${HANZO_API_KEY}"
models:
default:
- enso
- enso-auto
- enso-flash
- enso-pro
- enso-ultra
- zen5
- zen5-pro
+1 -1
View File
@@ -11,7 +11,7 @@ Hanzo Chat provides a full-featured AI chat experience. This page covers all maj
Switch between models mid-conversation or start new chats with any available model:
- **enso** — the frontier family: `enso-flash`, `enso`, `enso-ultra`
- **Enso** — `enso-auto`, and the paid tiers `enso-flash`, `enso-pro`, `enso-ultra`: [which for what, and prices](/docs/models/enso)
- **Zen** — `zen5`, `zen5-pro`, `zen5-coder`, `zen5-flash`, plus `zen-vl` for vision and `zen-guard` for safety
- **Carried models** — models from outside labs are available too, picked from the same model menu
- **Model comparison** — run the same prompt against multiple models side-by-side
+4 -2
View File
@@ -24,8 +24,10 @@ Pick by the shape of the job, then copy the id from the catalogue:
| Use case | Reach for |
|----------|-----------|
| General chat | `enso-flash` — cheapest Enso tier, 262K context |
| Hard reasoning | `enso` or `enso-ultra` |
| General chat | `enso-auto` — free models, or on a paid plan the [Enso tier](/docs/models/enso) your reasoning depth asks for |
| Volume, fast answers | `enso-flash` |
| Coding and analysis | `enso-pro` |
| The hardest problems | `enso-ultra` |
| Code generation | `zen5-coder` |
| Vision | `zen-vl` |
| Content moderation | `zen-guard` |
+1 -1
View File
@@ -78,7 +78,7 @@ The house vocabulary. None of these is guessable, so each gets a sentence.
| **ZAP** | Zero-Copy App Proto — the binary protocol our services speak to each other. |
| **visor** | The compute you rent: machines, GPUs, clusters. |
| **Zen** | The generative model family: open weights, for reasoning, code, vision, speech and embeddings. [Zen](/docs/models/zen). |
| **Enso** | The router: picks the model for each request (`model: "auto"`), and the `enso-*` family that serves the choice under one name. [Enso](/docs/models/enso). |
| **Enso** | Hanzo's own model family: a free lane (`enso-auto`) and three paid tiers, `enso-flash`, `enso-pro` and `enso-ultra`, each a chain of frontier models under one price; also the router behind `model: "auto"`. [Enso](/docs/models/enso). |
| **Kai** | The decision model: typed, calibrated answers to bounded questions, no generated text. [Kai](/docs/models/kai). |
| **Hanzo Decision** | Kai, Decision Programs, Decision Packages and policy, served at `POST /v1/decisions`. |
| **Decision Program** | A versioned graph of typed nodes — deterministic, Kai, Zen, solver, human, policy — over evidence. |
@@ -29,7 +29,8 @@ hanzo --claude --cloud --model enso-ultra
```
- **Model calls** go to `https://api.hanzo.ai`. The wrapper points Claude Code at it with `ANTHROPIC_BASE_URL` and sends your Hanzo token as the bearer in `ANTHROPIC_AUTH_TOKEN`, and clears any `ANTHROPIC_API_KEY` in your shell so one credential is in play. The token reaches the process through its environment, never its arguments.
- **The model** is `enso-auto` unless you set another with `--model`, `ANTHROPIC_MODEL` or `model` in `~/.hanzo/settings.json`. Claude Code is handed a `claude-*` name so it grants the model's real context window, and the wrapper maps that name back to the Hanzo model before the request leaves the process.
- **The model** is `enso-auto` unless you set another with `--model`, `ANTHROPIC_MODEL` or `model` in `~/.hanzo/settings.json`. `--model zen6` runs Zen 6, the open-weights model. Claude Code is handed a `claude-*` name so it grants the model's real context window, and the wrapper maps that name back to the Hanzo model before the request leaves the process.
- **Claude Code's own slots** are Enso tiers: Haiku, which runs background work and routine turns, is `enso-flash`; Sonnet is `enso-pro`; Opus and Fable are `enso-ultra`. [Enso](/docs/models/enso#claude-code) has what each tier costs and which models answer it.
- **Usage** is metered into your org at api.hanzo.ai, so it appears in the cloud whichever machine you ran on. Your org's cloud tools are added beside the toolset, because the process already holds your token.
- **Claude Code's home** for the run is `~/.hanzo/claude`, so its saved model choice and your Hanzo settings do not overwrite each other.
@@ -74,13 +74,15 @@ The extensions read the same `~/.claude/settings.json` as the CLI:
"apiKeyHelper": "/Users/you/.local/bin/hanzo auth token",
"env": {
"ANTHROPIC_BASE_URL": "https://api.hanzo.ai",
"ANTHROPIC_MODEL": "enso",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "enso"
"ANTHROPIC_MODEL": "enso-auto",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "enso-flash",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "enso-pro",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "enso-ultra"
}
}
```
The helper prints your sign-in's current token, so no key is written into the file. In a terminal, `hanzo --claude --cloud` does the same for one run and edits nothing.
The helper prints your sign-in's current token, so no key is written into the file. Each slot names the [Enso tier](/docs/models/enso) that `hanzo --claude --cloud` puts there. In a terminal, `hanzo --claude --cloud` does the same for one run and edits nothing.
### Codex, in the app, the IDE extension and the CLI
+1 -1
View File
@@ -11,7 +11,7 @@ ones you can download, and which ids the gateway serves right now.**
| Family | Role | Weights | Reach it at | Status |
|---|---|---|---|---|
| **[Enso](/docs/models/enso)** | routes and orchestrates: picks the model, context and tools per request | router code open ([hanzoai/engine](https://github.com/hanzoai/engine)); family SKUs hosted | `model: "auto"` and `enso-*` ids | shipped |
| **[Enso](/docs/models/enso)** | routes: three paid tiers, each a chain of frontier models under one id and one price, and the `auto` router | router code open ([hanzoai/engine](https://github.com/hanzoai/engine)); tiers hosted | `enso-auto`, `enso-flash`, `enso-pro`, `enso-ultra`; `model: "auto"` | shipped |
| **[Kai](/docs/models/kai)** | decides: typed, calibrated answers to bounded questions | hosted, not published; served by API only | `model: "kai"` on [`POST /v1/decisions`](/docs/decisions) | live: kai-1.2, $0.021 per million input tokens |
| **[Zen](/docs/models/zen)** | reasons: agentic coding that runs locally, marketing copy and assets; also vision, speech, embeddings | open, on [Hugging Face](https://huggingface.co/zenlm) | `zen*` ids on `/v1/chat/completions` | shipped |
| **Policy** | governs: deterministic allow / ask / deny | — | your rules, in every Decision Program | a part of Hanzo Decision, not a model |
+3 -10
View File
@@ -163,13 +163,6 @@ Use Slack's noun everywhere a Slack user expects it. Never invent a synonym.
| Fact | Value |
|---|---|
| Models | 536 |
| Providers | 57 |
| Enso tiers | `enso-flash` · `enso` · `enso-ultra` |
| Escalate past Flash | 1 in 5 |
| Saved vs top rate | 69% |
| Best case | 83% |
<Callout type="warn" title="Not 90%">
The calculator will not produce it. A hard-coded 89% was published once and pulled.
</Callout>
| Catalogue | every id `GET /v1/models` lists, live at [Models](/docs/models) |
| Default | `enso-auto` |
| Enso tiers | `enso-flash` · `enso-pro` · `enso-ultra`, priced at [Enso](/docs/models/enso) |