opencode-agent[bot]
da4730e4a4
deploy / deploy (push) Has been cancelled
docs-locale-sync / sync-locales (push) Has been cancelled
generate / generate (push) Has been cancelled
nix-eval / nix-eval (push) Has been cancelled
publish / version (push) Has been cancelled
typecheck / typecheck (push) Has been cancelled
publish / build-cli (push) Has been cancelled
publish / sign-cli-windows (push) Has been cancelled
publish / build-electron (map[bun_install_flags:--os=darwin --cpu=arm64 host:macos-26 platform_flag:--mac --arm64 target:aarch64-apple-darwin]) (push) Has been cancelled
publish / build-electron (map[bun_install_flags:--os=darwin --cpu=x64 host:macos-26-intel platform_flag:--mac --x64 target:x86_64-apple-darwin]) (push) Has been cancelled
publish / build-electron (map[host:blacksmith-4vcpu-ubuntu-2404 platform_flag:--linux target:x86_64-unknown-linux-gnu]) (push) Has been cancelled
publish / build-electron (map[host:blacksmith-4vcpu-ubuntu-2404-arm platform_flag:--linux --arm64 target:aarch64-unknown-linux-gnu]) (push) Has been cancelled
publish / build-electron (map[host:blacksmith-4vcpu-windows-2025 platform_flag:--win target:x86_64-pc-windows-msvc]) (push) Has been cancelled
publish / build-electron (map[host:windows-2025 platform_flag:--win --arm64 target:aarch64-pc-windows-msvc]) (push) Has been cancelled
publish / publish (push) Has been cancelled
289 lines
16 KiB
Plaintext
289 lines
16 KiB
Plaintext
---
|
|
title: Go
|
|
description: Low cost subscription for open coding models.
|
|
---
|
|
|
|
import config from "../../../config.mjs"
|
|
export const console = config.console
|
|
export const email = `mailto:${config.email}`
|
|
|
|
OpenCode Go is a low cost subscription — **$5 for your first month**, then **$10/month** — that gives you reliable access to popular open coding models.
|
|
|
|
Go works like any other provider in OpenCode. You subscribe to OpenCode Go and
|
|
get your API key. It's **completely optional** and you don't need to use it to
|
|
use OpenCode.
|
|
|
|
It is designed primarily for international users and provides stable global access.
|
|
|
|
---
|
|
|
|
## Background
|
|
|
|
Open models have gotten really good. They now reach performance close to
|
|
proprietary models for coding tasks. And because many providers can serve them
|
|
competitively, they are usually far cheaper.
|
|
|
|
However, getting reliable, low latency access to them can be difficult. Providers
|
|
vary in quality and availability.
|
|
|
|
:::tip
|
|
We tested a select group of models and providers that work well with OpenCode.
|
|
:::
|
|
|
|
To fix this, we did a couple of things:
|
|
|
|
1. We tested a select group of open 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 Go gives you access to these models for **$5 for your first month**, then **$10/month**.
|
|
|
|
---
|
|
|
|
## How it works
|
|
|
|
OpenCode Go works like any other provider in OpenCode.
|
|
|
|
1. You sign in to **<a href={console}>OpenCode Zen</a>**, subscribe to Go, and
|
|
copy your API key.
|
|
2. You run the `/connect` command in the TUI, select `OpenCode Go`, and paste
|
|
your API key.
|
|
3. Run `/models` in the TUI to see the list of models available through Go.
|
|
|
|
:::note
|
|
Only one member per workspace can subscribe to OpenCode Go.
|
|
:::
|
|
|
|
The current list of models includes:
|
|
|
|
- **Grok 4.5**
|
|
- **GLM-5.3**
|
|
- **GLM-5.2**
|
|
- **GLM-5.1**
|
|
- **GPT 5.6 Luna**
|
|
- **Kimi K3**
|
|
- **Kimi K2.7 Code**
|
|
- **Kimi K2.6**
|
|
- **MiMo-V2.5**
|
|
- **MiMo-V2.5-Pro**
|
|
- **MiniMax M3**
|
|
- **MiniMax M2.7**
|
|
- **Muse Spark 1.2 Contributor**
|
|
- **Qwen3.8 Max**
|
|
- **Qwen3.7 Max**
|
|
- **Qwen3.7 Plus**
|
|
- **Qwen3.6 Plus**
|
|
- **DeepSeek V4 Pro**
|
|
- **DeepSeek V4 Flash**
|
|
- **Hy3**
|
|
|
|
The list of models may change as we test and add new ones.
|
|
|
|
---
|
|
|
|
## Usage limits
|
|
|
|
OpenCode Go includes the following limits:
|
|
|
|
- **5 hour limit** — $12 of usage
|
|
- **Weekly limit** — $30 of usage
|
|
- **Monthly limit** — $60 of usage
|
|
|
|
Limits are defined in dollar value. This means your actual request count depends on the model you use. Cheaper models like MiMo-V2.5 allow for more requests, while higher-cost models like GLM-5.2 allow for fewer.
|
|
|
|
The table below provides an estimated request count based on typical Go usage patterns:
|
|
|
|
| Model | requests per 5 hour | requests per week | requests per month |
|
|
| -------------------------- | ------------------- | ----------------- | ------------------ |
|
|
| Grok 4.5 | 120 | 300 | 600 |
|
|
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
|
|
| GLM-5.3 | 220 | 540 | 1,080 |
|
|
| GLM-5.2 | 880 | 2,150 | 4,300 |
|
|
| GLM-5.1 | 880 | 2,150 | 4,300 |
|
|
| Kimi K3 | 110 | 250 | 490 |
|
|
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
|
|
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
|
|
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
|
|
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
|
|
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
|
|
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
|
|
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
|
|
| Qwen3.8 Max | 160 | 400 | 810 |
|
|
| Qwen3.7 Max | 340 | 840 | 1,690 |
|
|
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
|
|
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
|
|
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
|
|
| DeepSeek V4 Flash | 7,600 | 18,900 | 37,800 |
|
|
| Hy3 | 4,300 | 10,750 | 21,500 |
|
|
|
|
The estimates are based on observed request patterns:
|
|
|
|
- Grok 4.5 — 1,100 input, 71,500 cached, 220 output tokens per request
|
|
- GLM-5.3/5.2/5.1 — 700 input, 52,000 cached, 150 output tokens per request
|
|
- GPT 5.6 Luna — 1,000 input, 50,000 cached, 220 output tokens per request
|
|
- Kimi K3 — 1,050 input, 76,500 cached, 300 output tokens per request
|
|
- Kimi K2.7/K2.6 — 870 input, 55,000 cached, 200 output tokens per request
|
|
- DeepSeek V4 Pro — 750 input, 82,000 cached, 290 output tokens per request
|
|
- DeepSeek V4 Flash — 410 input, 71,300 cached, 310 output tokens per request
|
|
- MiniMax M3 — 510 input, 56,000 cached, 190 output tokens per request
|
|
- MiniMax M2.7 — 300 input, 55,000 cached, 125 output tokens per request
|
|
- Muse Spark 1.2 Contributor — 620 input, 71,400 cached, 300 output tokens per request
|
|
- MiMo-V2.5 — 830 input, 71,500 cached, 295 output tokens per request
|
|
- MiMo-V2.5-Pro — 790 input, 86,000 cached, 305 output tokens per request
|
|
- Qwen3.8 Max — 420 input, 66,000 cached, 200 output tokens per request
|
|
- Qwen3.7 Max — 420 input, 66,000 cached, 200 output tokens per request
|
|
- Qwen3.7 Plus — 500 input, 57,000 cached, 190 output tokens per request
|
|
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
|
|
- Hy3 — 830 input, 71,500 cached, 295 output tokens per request
|
|
|
|
The estimates are also based on the following prices per 1M tokens and the monthly usage included with each model:
|
|
|
|
| Model | Input | Output | Cached Read | Cached Write | Usage |
|
|
| ---------------------------- | ------ | ------ | ----------- | ------------ | ----- |
|
|
| Grok 4.5 | $2.00 | $6.00 | $0.30 | - | $15 |
|
|
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | $15 |
|
|
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | $15 |
|
|
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | $15 |
|
|
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | $60 |
|
|
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | $60 |
|
|
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | $15 |
|
|
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | $60 |
|
|
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | $60 |
|
|
| MiMo V2.5 | $0.14 | $0.28 | $0.0028 | - | $60 |
|
|
| MiMo V2.5 Pro | $0.435 | $0.87 | $0.003625 | - | $15 |
|
|
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | $60 |
|
|
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | $60 |
|
|
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | $60 |
|
|
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | $60 |
|
|
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | $15 |
|
|
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | $60 |
|
|
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | $60 |
|
|
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | $60 |
|
|
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | $60 |
|
|
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | $60 |
|
|
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | $15 |
|
|
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | $15 |
|
|
| DeepSeek V4 Flash (Off-Peak) | $0.22 | $0.66 | $0.007 | - | $30 |
|
|
| DeepSeek V4 Flash (Peak) | $0.44 | $1.32 | $0.014 | - | $30 |
|
|
| Hy3 | $0.14 | $0.58 | $0.035 | - | $60 |
|
|
|
|
**DeepSeek V4 Flash / Pro:** Peak hours are 01:00-04:00 and 06:00-10:00 UTC; all other hours are Off-Peak. [Learn more](https://api-docs.deepseek.com/quick_start/pricing/).
|
|
|
|
You can track your current usage in the **<a href={console}>console</a>**.
|
|
|
|
:::tip
|
|
If you reach the usage limit, you can continue using the free models.
|
|
:::
|
|
|
|
Usage limits may change as we learn from early usage and feedback.
|
|
|
|
---
|
|
|
|
### Usage beyond limits
|
|
|
|
If you also have credits on your Zen balance, you can enable the **Use balance**
|
|
option in the console. When enabled, Go will fall back to your Zen balance
|
|
after you've reached your usage limits instead of blocking requests.
|
|
|
|
---
|
|
|
|
### Why some models have lower usage
|
|
|
|
With Go, you pay $10/month and we aim to give you 6x that in usage.
|
|
|
|
For most models, we make this work through bulk discounts and reserved GPU capacity. We then pass those savings on to you through the 6x multiplier.
|
|
|
|
For some models, we haven't had the opportunity to negotiate a discount or host them at a lower cost, either because the model is new or because their public pricing is already discounted.
|
|
|
|
For these models, you still get a little more than if you paid the model providers directly; this is why their usage mulitplier is lower in the table above.
|
|
|
|
---
|
|
|
|
## Endpoints
|
|
|
|
You can also access Go models through the following API endpoints.
|
|
|
|
| Model | Model ID | Endpoint | AI SDK Package |
|
|
| -------------------------- | -------------------------- | ------------------------------------------------ | --------------------------- |
|
|
| Grok 4.5 | grok-4.5 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
|
|
| GPT 5.6 Luna | gpt-5.6-luna | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
|
|
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| MiMo-V2.5 | mimo-v2.5 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
|
|
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
|
|
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
|
|
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
|
|
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
|
|
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
|
|
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
|
|
| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
|
|
| Hy3 | hy3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
|
|
|
The [model id](/docs/config/#models) in your OpenCode config
|
|
uses the format `opencode-go/<model-id>`. For example, for Kimi K3, you would
|
|
use `opencode-go/kimi-k3` in your config.
|
|
|
|
---
|
|
|
|
### Models
|
|
|
|
You can fetch the full list of available models and their metadata from:
|
|
|
|
```
|
|
https://opencode.ai/zen/go/v1/models
|
|
```
|
|
|
|
---
|
|
|
|
## Privacy
|
|
|
|
| Model | Model training | Data retention |
|
|
| -------------------------- | -------------- | -------------- |
|
|
| Grok 4.5 | Not used | 30 days |
|
|
| GPT 5.6 Luna | Not used | 30 days |
|
|
| GLM-5.3 | Not used | 0 days |
|
|
| GLM-5.2 | Not used | 0 days |
|
|
| GLM-5.1 | Not used | 0 days |
|
|
| Kimi K3 | Not used | 0 days |
|
|
| Kimi K2.7 Code | Not used | 0 days |
|
|
| Kimi K2.6 | Not used | 0 days |
|
|
| MiMo-V2.5-Pro | Not used | 0 days |
|
|
| MiMo-V2.5 | Not used | 0 days |
|
|
| Qwen3.8 Max | Not used | 0 days |
|
|
| Qwen3.7 Max | Not used | 0 days |
|
|
| Qwen3.7 Plus | Not used | 0 days |
|
|
| Qwen3.6 Plus | Not used | 0 days |
|
|
| MiniMax M3 | Not used | 0 days |
|
|
| MiniMax M2.7 | Not used | 0 days |
|
|
| Muse Spark 1.2 Contributor | Yes | Not ZDR |
|
|
| DeepSeek V4 Pro | Not used | 0 days\* |
|
|
| DeepSeek V4 Flash | Not used | 0 days\* |
|
|
| Hy3 | Not used | 0 days |
|
|
|
|
- **Grok 4.5:** ZDR disables important API features that depend on stored data, including the stateful Responses API, Files and Collections, and the Batch API. [Learn more](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
|
|
- **GPT 5.6 Luna:** Abuse monitoring logs are generated for all API feature usage and retained for up to 30 days. [Learn more](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
|
|
- **Muse Spark 1.2 Contributor:** Heavily discounted token pricing in exchange for permission to use your prompts and completions to train future Meta models. [Learn more](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
|
|
- **DeepSeek:** ZDR agreement is renewed monthly. The current agreement is valid through August 31, 2026.
|
|
|
|
---
|
|
|
|
## Goals
|
|
|
|
We created OpenCode Go to:
|
|
|
|
1. Make AI coding **accessible** to more people with a low cost subscription.
|
|
2. Provide **reliable** access to the best open coding models.
|
|
3. Curate models that are **tested and benchmarked** for coding agent use.
|
|
4. Have **no lock-in** by allowing you to use any other provider with OpenCode as well.
|