runaiicloud
ModelsGPUsPricingDocsConnectCompareEnterprisePlayground
Log inGet started

[ connect — sdks & agents ]

Plug your agent into runaii.

runaii.cloud speaks both the OpenAI and Anthropic dialects, so every major coding agent works with one environment variable — no proxy daemon, no config DSL. Create a key, set two env vars, ship.

Step 0 — get a key:Create API key$1 free credits on signup, no card.

Claude Code

Anthropic dialect

Point Claude Code at runaii (env vars — set before launching):

sh
$ export ANTHROPIC_BASE_URL=https://api.runaii.cloud/api
export ANTHROPIC_AUTH_TOKEN=sk-runaii-… # your API key

Then launch normally — requests are metered to your runaii balance:

sh
$ claude

Model routing: use runaii/glm-5.3 or runaii/kimi-k3 with /model inside Claude Code.

Cursor

OpenAI dialect

Settings → Models → OpenAI API key → override base URL:

cursor
$ # Cursor settings JSON (Models → OpenAI API Key → override)
{
"apiKey": "sk-runaii-…",
"baseUrl": "https://api.runaii.cloud/v1"
}

Enable the runaii models you want (they appear after Verify):

Add model IDs exactly as runaii/glm-5.3-flash, runaii/kimi-k3, runaii/deepseek-v4-pro.

Cline

OpenAI dialect

Cline settings → API Provider → OpenAI Compatible:

cline
$ Base URL: https://api.runaii.cloud/v1
API Key: sk-runaii-…
Model ID: runaii/glm-5.3-flash

Codex CLI

OpenAI dialect

~/.codex/config.toml — point the OpenAI provider at runaii:

codex-cli
$ [model_providers.runaii]
name = "runaii"
base_url = "https://api.runaii.cloud/v1"
env_key = "RUNAII_API_KEY"
 
# then: profile.default_provider = "runaii"

Aider

OpenAI dialect

One env var pair — aider reads OpenAI-compatible endpoints natively:

aider
$ export OPENAI_API_BASE=https://api.runaii.cloud/v1
export OPENAI_API_KEY=sk-runaii-…
aider --model openai/runaii/glm-5.3

Any OpenAI/Anthropic SDK

OpenAI dialect

The two env vars every OpenAI-compatible tool understands:

openai-sdk
$ export OPENAI_API_BASE=https://api.runaii.cloud/v1
export OPENAI_API_KEY=sk-runaii-…

Anthropic tools: ANTHROPIC_BASE_URL=https://api.runaii.cloud/api + ANTHROPIC_AUTH_TOKEN.

Verify it works

liveMaking requestMaking request

One curl from the same shell — if this returns a completion, your agent will too:

curl
$ curl https://api.runaii.cloud/v1/chat/completions \
-H "Authorization: Bearer $RUNAII_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"runaii/glm-5.3-flash","messages":[{"role":"user","content":"ping"}]}'
liveMaking requestMaking request

Using a tool that's not listed? Anything that speaks OpenAI or Anthropic works — check the docs for the base URLs, or hit FAQ for limits.

runaiicloud

Serverless inference, dedicated GPUs, and training for open models. OpenAI- and Anthropic-compatible APIs.

© 2026 runaii

Platform

Model libraryGPUsPricingCompare providersSavings calculatorDocsServerlessDeploymentsTrainingBatch API

Developers

PlaygroundCookbookCLIAgents / MCPResearch notesUI/UX systemUse casesTutorialsModel advisorBlogCustomersFAQ

Company

EnterpriseStartupsAboutCareersPartnersTrust centerSLAStatusChangelogrunaii chatSupportAPI keysTermsPrivacy