Grok 4.6
FlagshipxAI flagship (upgraded from 4.5), one of the strongest open coding models; ~169 requests per 5h.
Back to comparisonOpenCode Go
OpenCode · Anomaly
OpenCode Go
Plan Guide
Low-cost subscription for open coding models: $10/month with about 6x the subscription value in usage. A curated lineup of 24 tested open-source models works with OpenCode or any compatible agent. Note: the first-month $5 promo was removed on Aug 24.
24Models
$10Per month
6xUsage value
7,600V4 Flash 5h requests
Models
24 open models, all tested and benchmarked for agentic coding. August additions: GLM-5.3 / 5.3-Flash, LongCat-2.0, Qwen3.8 Flash, DeepSeek V4 Flash Vision; Grok upgraded from 4.5 to 4.6.
GLM-5.3 / GLM-5.3-Flash
Flash 2x promoZhipu’s new flagship and multimodal variant, added in August. GLM-5.3 ~220 requests/5h; 5.3-Flash gets limited-time 2x limits (~1,580 requests/5h).
Kimi K3
Moonshot flagship (2.8T params, 1M context); ~110 requests per 5h.
Qwen3.8 Max / Flash
Alibaba’s flagship and the new Flash tier; ~160 and ~5,400 requests per 5h respectively.
DeepSeek V4 Pro / Flash
Peak/off-peakV4 Pro ~3,450 requests/5h; V4 Flash ~7,600 with peak/off-peak pricing (off-peak is half price). V4 Flash Vision handles images.
MiniMax M3
Multimodal flagship; ~3,200 requests per 5h.
MiMo-V2.5
Best valueXiaomi’s ultra-cheap open model; ~30,100 requests per 5h.
Hy3
High-performance open model (8x usage marked); ~4,300 requests per 5h.
GPT 5.6 Luna
OpenAI open model; ~2,050 requests per 5h.
LongCat-2.0 / Muse Spark 1.2
New additions: LongCat-2.0 ~11,400 requests/5h; Muse Spark 1.2 Contributor (region-limited) ~45,300 requests/5h.
Plans
A single $10/mo tier with 6x usage value. Top up credit if needed, cancel anytime. The first-month $5 promo was removed on Aug 24.
Go
$10/mo$10/mo
Top up credit anytime · No lock-in
- $12 / 5h · $30 / week · $60 / month usage
- 24 curated open models (Grok 4.6, GLM-5.3, Kimi K3...)
- OpenAI / Anthropic compatible APIs, any agent
- Fall back to Zen balance when limits are reached
- No training on your data, 0-day retention for most models
- Cancel any time
Best for
Subscribe to Go →Developers who want the strongest open models at the lowest cost, and heavy agent users
Model usage
Estimated requests at typical usage patterns (per 5h / week / month).
| Model | 5 hours | Weekly | Monthly |
|---|---|---|---|
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| LongCat-2.0 | 11,400 | 28,500 | 57,000 |
| DeepSeek V4 Flash | 7,600 | 19,000 | 38,000 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Hy3 (8x) | 4,300 | 10,750 | 21,500 |
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
| GLM-5.3-Flash | 1,580 | 3,950 | 7,900 |
| GLM-5.3 | 220 | 550 | 1,100 |
| Grok 4.6 | 169 | 420 | 840 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Kimi K3 | 110 | 250 | 490 |
支持的编程工具
OpenCodeClaude CodeCursorClineRoo CodeKilo CodeCherry Studio
Usage limits
Limits are dollar-based: $12 per 5h, $30 per week, $60 per month. Expensive models consume budget faster. Free models remain available after you hit limits. DeepSeek V4 models use peak/off-peak pricing (2x during peak windows).
Rolling 5-hour
$12 of usage per rolling 5-hour window.
Weekly
$30 per week, reset weekly, no rollover.
Monthly
$60 per month - about 6x your $10 subscription.
Balance fallback
Enable "Use balance" in the console to continue from your Zen balance after limits.
How to connect
- Sign in at opencode.ai, subscribe to Go and copy your API key
- In the OpenCode TUI run /connect, pick OpenCode Go, paste your key
- Model IDs use the format opencode-go/<model-id> (e.g. opencode-go/kimi-k3)
- OpenAI / Anthropic / Responses compatible endpoints work with Claude Code, Cursor and more
- Web search is enabled when using the OpenCode Go provider (since Aug 20)
Privacy
- No model is used for training
- Most models have 0-day data retention (GLM, Kimi, Qwen, DeepSeek, MiniMax, MiMo)
- Grok 4.6 and GPT 5.6 Luna retain 30 days (abuse monitoring)
- DeepSeek V4 Flash zero-data-retention agreement renews monthly
Frequently Asked Questions
What is OpenCode Go?
OpenCode Go is Anomaly’s low-cost subscription for open coding models: $10/month, giving about 6x the subscription value in usage across 24 curated open models, usable in OpenCode or any OpenAI/Anthropic compatible agent.
Is the first month still $5?
No. OpenCode removed the Go first-month $5 discount on Aug 24 (changelog v1.18.24). The plan is now a flat $10/month, cancelable anytime.
How do usage limits work?
Limits are dollar-based: $12 per 5 hours, $30 per week, $60 per month. Request counts depend on model price - DeepSeek V4 Flash allows ~7,600 requests/5h while Kimi K3 allows ~110. After limits you can fall back to Zen balance or free models.
Which models are included?
24 models: Grok 4.6, GLM-5.3/5.3-Flash (limited 2x)/5.2/5.1, GPT 5.6 Luna, Kimi K3/K2.7 Code/K2.6, LongCat-2.0, MiMo-V2.5/-Pro, MiniMax M3/M2.7, Muse Spark 1.2 Contributor (region-limited), Qwen3.8 Max/Flash, Qwen3.7 Max/Plus, Qwen3.6 Plus, DeepSeek V4 Pro/Flash/Flash Vision Exp, Hy3. The list keeps growing.
Is my data used for training?
No model uses your data for training. Most models keep 0-day retention; Grok 4.6 and GPT 5.6 Luna keep 30 days of logs for abuse monitoring.