Best API & Subscription for Cline

For heavy daily Cline use, the alternative to topping up OpenRouter credits is a cost-optimized API, and Standard Compute is built into Cline's provider list from Cline 4.1.25 (October 16, 2026): pick Standard Compute under API Provider, enter https://api.stdcmpt.com/v1 and your key (on 4.1.24 and older, choose OpenAI Compatible with the same settings). Its router sends each Plan and Act step to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), so one key replaces several provider profiles, on a fixed plan from $19/month with an enforced compute budget. OpenRouter stays cheaper for light or bursty use; OpenCode Go and GLM coding subscriptions are candidates where Cline supports them.

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.

This page compares which API provider to connect to Cline. For Claude, GPT and open models at one monthly price, with ClinePass and Anthropic's per-token prices side by side and the settings to copy, see Is there a flat-rate API for Cline?

Light or occasional use
Run a small Cline task with a lower-cost model before buying a subscription. Compare its result and consumption with a supported coding plan; repeated tool calls and large file context can change the economics.
Daily use, cost-optimized
Standard Compute fits when you want each Cline step on 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. It runs on one monthly plan, so check that your Cline tasks fit the allowance: Plan and Act calls both consume compute, and no automatic overage charges means requests stop at the budget.

API and subscription options for Cline

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
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
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 $20 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.
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. The built-in Standard Compute provider comes from Cline's v4.1.25, CLI v3.0.72 and Desktop v0.0.47 release notes (October 16, 2026: "Adds the Boundless and Standard Compute providers") and the provider catalog and settings screens in Cline's source at tag v4.1.25, read on October 16, 2026. OpenCode Go prices were checked on October 13, 2026, DevPass prices on September 5, 2026. Cline v4.1.25 release notes · Cline CLI v3.0.72 release notes · Cline: authorizing a provider. Spot an error? Tell us.

Pick Standard Compute in Cline's API Provider list

Cline settings
# Cline 4.1.25+ (VS Code, JetBrains). On 4.1.24 and older: OpenAI Compatible
API Provider               Standard Compute
Base URL                   https://api.stdcmpt.com/v1
OpenAI Compatible API Key  YOUR_API_KEY
Model ID                   standardcompute

# Cline CLI 3.0.72+
cline auth -p standardcompute -k "$STANDARDCOMPUTE_API_KEY" -m standardcompute

Open Cline's settings with the gear icon and type Standard Compute in the API Provider search. The Base URL field starts empty, so enter https://api.stdcmpt.com/v1. In the CLI you can also run cline auth, choose Bring your own provider and pick Standard Compute; in Cline Desktop 0.0.47+, open Settings, then Providers. On Cline 4.1.24 or CLI 3.0.71 and older, choose OpenAI Compatible (cline auth -p openai-compatible ... -b https://api.stdcmpt.com/v1) with the same key and model.

Setup for one model in Cline: DeepSeek · GLM 5.3

Cline questions

Is Standard Compute built into Cline?
Yes, since October 16, 2026. Cline 4.1.25 for VS Code and JetBrains, Cline CLI 3.0.72 and Cline Desktop 0.0.47 list Standard Compute (provider id standardcompute) in their model catalog; the release notes say "Adds the Boundless and Standard Compute providers". In the extension, open settings, pick Standard Compute under API Provider, enter https://api.stdcmpt.com/v1 as Base URL, paste your key under OpenAI Compatible API Key and keep the Model ID standardcompute. In the CLI, run cline auth -p standardcompute -k "$STANDARDCOMPUTE_API_KEY" -m standardcompute. On 4.1.24 or CLI 3.0.71 and older, choose OpenAI Compatible with the same base URL, key and model.
How do people run Cline with Gemini 2.5 on hobby economics?
They cap the bill and move routine turns off the Pro model. Gemini 2.5 Pro lists at $1.25 / $10 per million tokens, and $2.50 / $15 once a prompt passes 200K tokens, which is how a heavy Cline week reaches $60. Standard Compute retires Gemini 2.5 Pro and Flash on October 20, 2026, so new selections use google/gemini-3.1-pro-preview ($2 / $12) and google/gemini-3.5-flash-lite ($0.30 / $2.50). Both are on every plan behind Cline's Standard Compute provider, and the monthly bill is the plan price: Starter $19 with a $20 budget, or Economy $39 with $41. Select both and use the model standardcompute so Flash-Lite takes the routine reads. A month of $60 weeks at Pro rates still uses a small budget up early, and then requests stop instead of billing.
How do people afford Opus-tier models as their daily driver in Cline?
Mostly by not sending every step to Opus. Claude Opus 5.5 lists at $4 / $20 per million tokens against Opus 5's $5 / $25, with cache reads at $0.20, so changing the model ID alone takes a $47 debugging session under $40. On Standard Compute, select Opus 5.5 with an efficient model and set Cline's model to standardcompute: hard steps go to Opus, routine reads and edits to the cheaper model, and the cost is a fixed plan, such as Pro at $249 a month with a $269 budget. Pinned to Opus all day, that budget covers five or six $47 sessions, so routing is what makes Opus a daily driver.
Which flat-rate inference do Cline BYOK users trust?
There are two kinds. ClinePass is Cline's own $9.99-a-month plan for 12 open-weight coding models, with 5-hour, weekly and monthly limits whose size Cline does not publish. Standard Compute is a built-in Cline provider from 4.1.25 (OpenAI Compatible on older versions, base URL https://api.stdcmpt.com/v1) and serves Claude and GPT as well as open models, from $19 a month with a published compute budget per plan ($20 on Starter, $95 on Standard), no 5-hour or weekly windows, and HTTP 402 instead of overage at the budget. ClinePass fits cheap open-model work inside Cline; a flat API fits when the meter you are replacing is Anthropic's.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Cline 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 keyCline 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 →