OpenCode
OpenCode Go
An AI subscription sold by OpenCode, not a tokenstat plan. Surfaces: coding. The list rates below are API prices for the same models, not what the seat costs.
Low-cost agentic coding subscription from OpenCode (Anomaly). $5 first month, then $10/mo; cancel any time. Works with OpenCode or any agent via the Go API key. Included usage is dollar-budgeted (~$12 per 5h, $30/week, $60/month), so request counts depend on model cost. Vendor estimates at typical Go patterns: Grok 4.6, Qwen3.8 Max, Kimi K2.7, DeepSeek V4 Pro, MiniMax M2.7 in the low hundreds per 5h; GPT-5.6 Luna ~2,050; GLM-5.3-Flash higher; Muse Spark 1.3/1.2 Contributor ~45,300/5h (~226,600/month, $0 list rate, limited regions). After limits, optional Zen balance top-up or free OpenCode models. One Go subscriber per workspace. Model roster changes as OpenCode retests providers. Source: https://opencode.ai/go and https://opencode.ai/docs/go/
Models on this plan
Representative lineup. $/MTok columns are published API list rates for comparison, not included subscription value. Checked . 15 with benchmark scores.
| Model | Tier | In $/M | Out $/M | Context | Score |
|---|---|---|---|---|---|
xAI: Grok 4.6xai/grok-4.6 | frontier | $2 | $6 | 524K | 1618Arena code |
Qwen3.8 Maxqwen/qwen3.8-max | frontier | $1.60 | $4.80 | 1.0M | 1671Arena code |
Mistral: GLM-5.3zai/glm-5.3 | strong | $0.4 | $1.40 | 1.3M | 1614Arena code |
Z.ai: GLM 5.3 Flashzai-org/glm-5.3-flash | strong | $0.015 | $0.05 | 1.3M | 1607Arena code |
OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-luna | strong | $0.06 | $0.37 | 1.1M | 37.3AA intel |
Moonshot: Kimi K2.7 Codemoonshotai/kimi-k2.7-code | strong | $0.275 | $1.10 | 271K | 25.8AA intel |
Moonshot: Kimi K2.6moonshot/kimi-k2.6 | strong | $0.275 | $1.10 | 262K | 1509Arena code |
MiniMax: M2.7MiniMax/MiniMax-M2.7 | strong | $0.08 | $0.32 | 262K | 22.8AA intel |
DeepSeek: V4 Prodeepseek/deepseek-v4-pro | strong | $0.348 | $0.696 | 1.1M | 30.4AA intel |
Qwen3.7 Maxqwen/qwen3.7-max | strong | $0.825 | $2.48 | 1.1M | 1517Arena code |
Qwen3.8 Flashqwen/qwen3.8-flash | fast | $0.11 | $0.39 | 1.0M | N/A |
Qwen3.7 Plusqwen/qwen3.7-plus | fast | $0.282 | $1.13 | 1.1M | 25.2AA intel |
Qwen3.6 Plusqwen/qwen3.6-plus | fast | $0.25 | $1.50 | 1M | 0AA intel |
DeepSeek: V4 Flashdeepseek/deepseek-v4-flash | fast | $0.035 | $0.07 | 1.1M | 1580Arena code |
MiMo V2.5xiaomi/mimo-v2.5 | fast | $0.14 | $0.28 | 1.1M | 0AA intel |
MiMo V2.5 Procrof/mimo-v2.5-pro | strong | $0.4 | $0.8 | 1.1M | 26AA intel |
Meta: Muse Spark 1.3 Contributoropencode-go/muse-spark-1.3-contributor | fast | $0.1 | $0.2 | 1.0M | N/A |
Explore around this plan
- All OpenCode subscription plansSticker ladder for this vendor
- OpenCode in the provider indexHosts, gateways, and model counts
- Full models catalogList rates, context, scores across providers
- Compare the first two linked modelsSide-by-side rates and scores
- Usage calculatorShape input/output/cache against list rates
- Vendor source pageAuthoritative sticker price and terms
Score sources on /benchmarks.
Get more from your AI subscription
Run sessions in workspaces, measure tokens across your tools, and compare plan-covered usage with its list-rate value. Use remote management when the work moves to another machine.
Data and list-price estimates may contain mistakes. Not investment advice.