Standard Compute

Roo Code shut down: the best API for where Roo users went

Roo Code shut down on May 15, 2026 and its repo is archived, so the API question now applies to where Roo users went: Cline (the extension Roo was forked from, and the Roo team's recommendation), ZooCode (the community fork that keeps Roo's modes) or Kilo Code. All three take the same OpenAI Compatible provider Roo did: base URL https://api.stdcmpt.com/v1 and model standardcompute put them on Standard Compute, whose router sends each step to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), on a plan from $19 a month with a $19 compute budget shared across every mode. Measure a full planning, editing and debugging task first, since each pass uses compute.

Guide updated 2026-10-15. Check each provider's current terms below.
Get your API key$0.25 trial for eligible new accounts, no card. Plans from $19/mo.
Light or occasional use
Move to Cline, ZooCode or Kilo Code first, then try an efficient model on routine tasks with stronger models reserved for difficult work. Compare the total calls in a complete task with the allowances of supported coding subscriptions.
Daily use, cost-optimized
In whichever successor you pick, Standard Compute sends each planning, editing and debugging step to the cheapest model that can do it, and for every model we vet providers for price, uptime and speed, with automatic fallback. Opt-in Europe or US Compliance rules apply per key, team or company, and we don't train on your prompts or store them. One monthly plan bounds the bill when your full workflow fits its budget; multiple modes do not receive separate allowances, so monitor combined use and expect a stop when the budget is exhausted.

API and subscription options for Roo Code

OptionPriceWhat you get
OpenCode Go$10 or $40/moNative OpenCode subscription: Go $10 a month, Go Plus $40. Each model has a monthly usage limit in dollars, with 5-hour and weekly windows set as shares of it. Single-member workspaces only. Source: opencode.ai
Standard Compute (us)From $19/moSmart routing sends each request to the cheapest model that can do it, or pin any model by its exact ID. Standard Compute starts at $19/month with a $19 monthly compute budget. Requests stop when that budget is exhausted until renewal or a plan change; there are no automatic overage charges. Requests are not slowed as the budget is used. It is a fixed bill with a finite allowance.
GLM Coding Plan (Z.ai)See current plansA coding subscription for the GLM model family. Check the current model access, client support and usage limits for the selected tier. Source: docs.z.ai
DevPass$29 / $79 / $179 per moMonthly allowances valued at provider rates, plus weekly premium-model fair-use limits. Useful when you want to select models; check the allowance for the models you actually use. Source: devpass.llmgateway.io
OpenRouterPay-as-you-goChoose models and providers through one API. Usage-based pricing can suit light or bursty work; estimate long agent sessions and review current fees and limits. Source: openrouter.ai

Prices and allowances can change. OpenCode Go prices were checked against its linked public pages on October 13, 2026, DevPass prices on September 5, 2026; other entries link to current plans without quoting an unverified price. Roo Code sunset notice · Roo Code repo (archived) · ZooCode. Spot an error? Tell us.

Roo Code questions

Is Roo Code still available?
No. Roo Code shut down on May 15, 2026: the extension's GitHub repo is archived, and Roo Code Cloud and Roo Code Router closed the same day. An installed copy may still run, but it gets no fixes or support for new models. The Roo team points users to Cline, and the README also names ZooCode, a fork the Roo community started.
Can I use Gemini 2.5 and Claude Sonnet 5 in Roo Code's successors without two provider accounts?
Yes, with a newer Gemini: Gemini 2.5 Pro is retired on October 20, 2026 and can no longer be added to a selection. One Standard Compute key serves google/gemini-3.1-pro-preview and anthropic/claude-sonnet-5 (and Sonnet 5.5) through the OpenAI Compatible provider at https://api.stdcmpt.com/v1 in Cline, ZooCode or Kilo Code. In ZooCode, which keeps Roo's modes, make one profile per model and assign them to modes, for example Sonnet for Code and Gemini for Architect; or select both on the Models page and use the model standardcompute to let routing pick per request. Both run on one bill, from $19 a month.
Who serves fast small models with a broader menu than Groq for Cline or ZooCode?
Standard Compute puts the small, fast-tier models on one key next to the frontier ones: GLM 5.3 Flash, Qwen 3.8 Flash, DeepSeek V4.1 Flash, GPT-6 Luna, Claude Haiku 5.5, Gemini 3.5 Flash-Lite and MiMo V2.6 Flash. Moving between them is a model ID change, not a new account. We do not publish speed guarantees, and Groq's own chips are built for raw tokens per second; the dashboard's request log shows each request's latency so you can compare on your own tasks. Plans start at $19 a month.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Roo Code version.
  2. Run a small task on a clean branch and review the result, elapsed time and compute used.
  3. Estimate your actual monthly workload before selecting a larger allowance.
Get your API keyRoo Code setup guide →Compare compute budgets →

Record your own results with the workload CSV and report template. These are blank templates, not published benchmark results.

Disclosure: this guide is maintained by Standard Compute, one of the options above. Choose based on task quality, supported features and total cost for your workload. Light usage may cost less on a usage-based API; sustained workloads need enough allowance on any subscription.

All flat-rate plans compared →The cheapest-tokens math →Plan compute for your team →