mirror of
https://github.com/aljazceru/opencode.git
synced 2025-12-22 18:24:21 +01:00
wip: zen
This commit is contained in:
95
packages/web/src/content/docs/zen.mdx
Normal file
95
packages/web/src/content/docs/zen.mdx
Normal file
@@ -0,0 +1,95 @@
|
||||
---
|
||||
title: Zen
|
||||
description: Curated list of models provided by opencode.
|
||||
---
|
||||
|
||||
import config from "../../../config.mjs"
|
||||
export const console = config.console
|
||||
export const email = `mailto:${config.email}`
|
||||
|
||||
opencode zen is a list of tested and verified models provided by the opencode team.
|
||||
|
||||
:::note
|
||||
opencode zen is currently in beta.
|
||||
:::
|
||||
|
||||
Zen works like any other provider in opencode. You login to opencode zen and get
|
||||
your API key. It's **completely optional** and you don't need to use it to use
|
||||
opencode.
|
||||
|
||||
---
|
||||
|
||||
## Background
|
||||
|
||||
There are a large number of models out there but only a few of
|
||||
these models work well as coding agents. Additionally, most providers are
|
||||
configured very differently; so you get very different performance and quality.
|
||||
|
||||
:::tip
|
||||
We tested a select group of models and providers that work well with opencode.
|
||||
:::
|
||||
|
||||
So if you are using a model through something like OpenRouter, you can never be
|
||||
sure if you are getting the best version of the model you want.
|
||||
|
||||
To fix this, we did a couple of things:
|
||||
|
||||
1. We tested a select group of models and talked to their teams about how to
|
||||
best run them.
|
||||
2. We then worked with a few providers to make sure these were being served
|
||||
correctly.
|
||||
3. Finally, we benchmarked the combination of the model/provider and came up
|
||||
with a list that we feel good recommending.
|
||||
|
||||
opencode zen is an AI gateway that gives you access to these models.
|
||||
|
||||
---
|
||||
|
||||
## Motivation
|
||||
|
||||
We created opencode zen to:
|
||||
|
||||
1. **Benchmark** the best models/providers for coding agents.
|
||||
2. Access to **highest quality**; we don't downgrade performance or route to cheaper providers.
|
||||
3. **Sell at cost**; the only markup is to cover our processing fees and any price
|
||||
drops will be passed along.
|
||||
4. **No lock-in**; you can use opencode zen with any other coding agent and you
|
||||
can use any other provider with opencode.
|
||||
|
||||
---
|
||||
|
||||
## How it works
|
||||
|
||||
opencode zen works like any other provider in opencode.
|
||||
|
||||
1. You sign in to **<a href={console}>opencode zen</a>** and get your API key.
|
||||
2. You run `opencode auth login` and select opencode zen and add your API key.
|
||||
3. Run `/models` in the TUI to see the list of models we recommend.
|
||||
|
||||
You are charged per request and you can add credits to your account.
|
||||
|
||||
---
|
||||
|
||||
## Pricing
|
||||
|
||||
Below are the models that we currently support and their prices **per 1M
|
||||
tokens**.
|
||||
|
||||
| Model | Input | Output |
|
||||
| ----- | ----- | ------ |
|
||||
| Qwen3 Coder 480B | $0.38 | $0.50 |
|
||||
| Grok Code Fast 1 | Free | Free |
|
||||
| Sonnet 4 | Soon | Soon |
|
||||
|
||||
:::note
|
||||
We add a small markup to cover our costs.
|
||||
:::
|
||||
|
||||
A couple of notes:
|
||||
|
||||
- These are the raw prices based on the provider we are using internally. We
|
||||
charge a small markup on top of this to cover our processing fees.
|
||||
- Grok Code Fast 1 is currently free on opencode till Sep 10th. The xAI team is
|
||||
using this time to collect feedback and improve Grok Code.
|
||||
|
||||
<a href={email}>Contact us</a> if you have any questions.
|
||||
Reference in New Issue
Block a user