AI · Subscription

OpenCode Go

A low-cost subscription for popular open coding models — $5 for your first month, then $10/month. Reliable access to GLM, Kimi, MiMo, MiniMax, Qwen, and DeepSeek through OpenCode.

💰 Price: $5 first month · $10/mo 🌍 Regions: US · EU · Singapore 🔓 Optional: Not required to use OpenCode 🔒 Privacy: Zero-retention, no training

OpenCode Go is designed primarily for international users, with models hosted across three regions for stable global access. Providers follow a zero-retention policy and do not use your data for model training.

How It Works

Sign in to OpenCode Zen, subscribe to Go, and copy your API key.
Run the /connect command in the TUI, select OpenCode Go, and paste your API key.
Run /models in the TUI to see the list of models available through Go.

Only one member per workspace can subscribe to OpenCode Go.

Available Models

GLM-5.2 / GLM-5.1
Kimi K2.7 Code / Kimi K2.6
MiMo-V2.5 / MiMo-V2.5-Pro
MiniMax M3 / MiniMax M2.7
Qwen3.7 Max / Qwen3.7 Plus / Qwen3.6 Plus
DeepSeek V4 Pro / DeepSeek V4 Flash

The list may change as new models are tested and added. Use the model ID format opencode-go/<model-id> in your config (e.g. opencode-go/kimi-k2.7-code).

Usage Limits

Limits are defined in dollar value — your actual request count depends on which model you use.

Period	Limit
5-hour limit	$12 of usage
Weekly limit	$30 of usage
Monthly limit	$60 of usage

Estimated Requests per Period

Model	Per 5 hrs	Per week	Per month
GLM-5.2 / 5.1	880	2,150	4,300
Kimi K2.7 Code	1,350	4,630	9,250
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
Qwen3.7 Max	950	2,390	4,770
Qwen3.7 Plus	4,300	10,800	21,600
Qwen3.6 Plus	3,300	8,200	16,300
DeepSeek V4 Pro	3,450	8,550	17,150
DeepSeek V4 Flash	31,650	79,050	158,150

If you reach the limit, you can continue using the free models. If you have credits on your Zen balance, enable Use balance in the console to fall back after limits are hit.

Pricing per 1M Tokens

Model	Input	Output	Cached Read	Cached Write
GLM-5.2 / 5.1	$1.40	$4.40	$0.26	—
Kimi K2.7 Code	$0.95	$4.00	$0.19	—
Kimi K2.6	$0.95	$4.00	$0.16	—
MiMo V2.5	$0.14	$0.28	$0.0028	—
MiMo V2.5 Pro	$1.74	$3.48	$0.0145	—
MiniMax M3	$0.30	$1.20	$0.06	—
MiniMax M2.7	$0.30	$1.20	$0.06	$0.375
Qwen3.7 Max	$2.50	$7.50	$0.50	$3.125
Qwen3.7 Plus (≤256K)	$0.40	$1.60	$0.04	$0.50
Qwen3.7 Plus (>256K)	$1.20	$4.80	$0.12	$1.50
Qwen3.6 Plus (≤256K)	$0.50	$3.00	$0.05	$0.625
Qwen3.6 Plus (>256K)	$2.00	$6.00	$0.20	$2.50
DeepSeek V4 Pro	$1.74	$3.48	$0.0145	—
DeepSeek V4 Flash	$0.14	$0.28	$0.0028	—

API Endpoints

Model	Model ID	SDK Package
GLM-5.2	`glm-5.2`	`@ai-sdk/openai-compatible`
GLM-5.1	`glm-5.1`	`@ai-sdk/openai-compatible`
Kimi K2.7 Code	`kimi-k2.7-code`	`@ai-sdk/openai-compatible`
Kimi K2.6	`kimi-k2.6`	`@ai-sdk/openai-compatible`
MiMo-V2.5	`mimo-v2.5`	`@ai-sdk/openai-compatible`
MiMo-V2.5-Pro	`mimo-v2.5-pro`	`@ai-sdk/openai-compatible`
DeepSeek V4 Pro	`deepseek-v4-pro`	`@ai-sdk/openai-compatible`
DeepSeek V4 Flash	`deepseek-v4-flash`	`@ai-sdk/openai-compatible`
MiniMax M3	`minimax-m3`	`@ai-sdk/anthropic`
MiniMax M2.7	`minimax-m2.7`	`@ai-sdk/anthropic`
Qwen3.7 Max	`qwen3.7-max`	`@ai-sdk/anthropic`
Qwen3.7 Plus	`qwen3.7-plus`	`@ai-sdk/anthropic`
Qwen3.6 Plus	`qwen3.6-plus`	`@ai-sdk/anthropic`

All models use the endpoint https://opencode.ai/zen/go/v1/chat/completions (OpenAI-compatible) or https://opencode.ai/zen/go/v1/messages (Anthropic-compatible).

Full model list: https://opencode.ai/zen/go/v1/models

Privacy

Models are hosted in the US, EU, and Singapore. Providers follow a zero-retention policy and do not use your data for model training.

Goals

Make AI coding accessible with a low-cost subscription.
Provide reliable access to the best open coding models.
Curate models that are tested and benchmarked for coding agent use.
No lock-in — use any other provider with OpenCode as well.

Get Started

Subscribe to Go → Official Docs GitHub

Browse the rest of the Dump collection.