docs: zen

This commit is contained in:
Jay V
2025-09-15 21:05:47 -04:00
parent 2c61b39088
commit 52fa7840c2
2 changed files with 46 additions and 48 deletions

View File

@@ -4,6 +4,8 @@ description: Get started with opencode.
---
import { Tabs, TabItem } from "@astrojs/starlight/components"
import config from "../../../config.mjs"
export const console = config.console
[**opencode**](/) is an AI coding agent built for the terminal.
@@ -60,7 +62,7 @@ You can also install it with the following:
#### Windows
Right now the automatic installation methods do not work properly on Windows. However you can grab the binary from the [Releases](https://github.com/sst/opencode/releases).
Currently, the automatic installation methods do not work properly on Windows. However you can grab the binary from the [Releases](https://github.com/sst/opencode/releases).
---
@@ -68,9 +70,14 @@ Right now the automatic installation methods do not work properly on Windows. Ho
With opencode you can use any LLM provider by configuring their API keys.
We recommend signing up for [Claude Pro](https://www.anthropic.com/news/claude-pro) or [Max](https://www.anthropic.com/max), it's the most cost-effective way to use opencode.
If you are new to using LLM providers, we recommend using [opencode zen](/docs/zen).
It's a curated list of models that have been tested and verified by the opencode
team.
Once you've signed up, run `opencode auth login` and select Anthropic.
1. Sign in to **<a href={console}>opencode zen</a>** and put in your billing
details.
2. Copy your API key.
3. Run `opencode auth login`, select opencode, and add your API key.
```bash
$ opencode auth login
@@ -78,13 +85,7 @@ $ opencode auth login
┌ Add credential
◆ Select provider
│ ● Anthropic
│ ○ OpenAI
│ ○ Google
│ ○ Amazon Bedrock
│ ○ Azure
│ ○ DeepSeek
│ ○ Groq
│ ● opencode
│ ...
```

View File

@@ -57,14 +57,19 @@ You are charged per request and you can add credits to your account.
---
## Goals
## Endpoints
We created opencode zen to:
You can also access our models through the following API endpoints.
1. **Benchmark** the best models/providers for coding agents.
2. Have access to the **highest quality** options and not downgrade performance or route to cheaper providers.
3. Pass along any **price drops** by selling at cost; so the only markup is to cover our processing fees.
4. Have **no lock-in** by allowing you to use it with any other coding agent. And always let you use any other provider with opencode as well.
| Model | Mode ID | Endpoint | AI SDK Package |
| ---------------- | ---------------- | --------------------------------------------- | --------------------------- |
| GPT-5 | gpt-5 | `https://opencode.ai/zen/v1/responses` | `@ai-sdk/openai` |
| Claude Sonnet 4 | claude-sonnet-4 | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` |
| Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` |
| Claude Opus 4.1 | claude-opus-4-1 | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3 Coder 480B | qwen3-coder | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Grok Code Fast 1 | grok-code | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2 | kimi-k2 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` |
---
@@ -88,35 +93,27 @@ tokens**.
Credit card fees are passed along at cost; we dont charge anything beyond that.
:::
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 for a limited time. The xAI team is
using this time to collect feedback and improve Grok Code.
Grok Code Fast 1 is currently free on opencode for a limited time. 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.
---
## Model Endpoints
| Model | Mode ID | Endpoint | AI SDK Package |
| ---------------- | ---------------- | --------------------------------------------- | --------------------------- |
| GPT-5 | gpt-5 | `https://opencode.ai/zen/v1/responses` | `@ai-sdk/openai` |
| Claude Sonnet 4 | claude-sonnet-4 | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` |
| Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` |
| Claude Opus 4.1 | claude-opus-4-1 | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3 Coder 480B | qwen3-coder | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Grok Code Fast 1 | grok-code | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2 | kimi-k2 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` |
---
## Privacy
1. All our models are hosted in the US.
2. Our providers follow a zero-retention policy and do not use your data for model training, with the following exceptions:
All our models are hosted in the US. Our providers follow a zero-retention policy and do not use your data for model training, with the following exceptions:
- Grok Code Fast 1: During its free period, collected data may be used to improve Grok Code.
- OpenAI APIs: Requests are retained for 30 days in accordance with [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
- Anthropic APIs: Requests are retained for 30 days in accordance with [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
---
## Goals
We created opencode zen to:
1. **Benchmark** the best models/providers for coding agents.
2. Have access to the **highest quality** options and not downgrade performance or route to cheaper providers.
3. Pass along any **price drops** by selling at cost; so the only markup is to cover our processing fees.
4. Have **no lock-in** by allowing you to use it with any other coding agent. And always let you use any other provider with opencode as well.