Skip to content
Agents tracked: 444 Releases (7d): 644 Agent status: 3 with issuesSince last limit reset: Claude 31d · Codex 3d Updated Oct 23, 2026
AgentGid
✦ Ask

Model APIs and gateways · by RightNow AI, Inc.

RunInfra

A hosted API for open-weight models (GLM, DeepSeek, Qwen, Nemotron and others) that speaks both the OpenAI Chat Completions and Anthropic Messages formats at one base URL, billed per token or through monthly coding plans.

You can point Claude Code, Codex, Aider or an existing OpenAI/Anthropic SDK at open models by changing a base URL and key, without renting or tuning GPUs yourself.

API (paid)Free tierCommercial OK

Open runinfra.ai ↗ agent.md

For your project

Official API
Official API · Paid Per-key requests per minute: 10,000 before the first credit purchase, 50,000 after; tokens-per-minute tier per model grows with lifetime purchases; every 429 carries Retry-After
“RunInfra serves open models for agents and apps through OpenAI-compatible and Anthropic-compatible Model APIs at https://api.runinfra.ai/v1, billed per token.” runinfra.ai/llms.txt
Key
Needed
“The endpoint needs a workspace API key, sent as `Authorization: Bearer` or `x-api-key`.” runinfra.ai/docs/api-reference/models.md
Formats
JSON
Data download
Not stated
Price
Free tier · from $10/mo $1 credit once on signup (never expires); then pay-as-you-go top-ups from $5, per-token prices per model
“Starter: $10 a month. About $12 of usage a month, paced as $2.77 a week and $1.11 per 5 hours.” runinfra.ai/llms.txt
License
RunInfra Legal Terms (RightNow AI, Inc.) Use of the hosted model API; you own the outputs; each open model's own license (Apache 2.0, MIT, Llama etc.) also applies; reselling GPU access is not allowed without authorization
Commercial use
Commercial use OK
“You own the outputs generated by your deployed pipelines. We do not use your API inputs or outputs to train any models or for any purpose other than providing the Services.” runinfra.ai/terms-of-service
Credit
Not stated
Embedding
Embedding unclear
Using the website
Paid

Read on RunInfra's own pages on Oct 24, 2026 · license or terms · API docs · pricing. Check the license page before you ship.

For your agent

  • Use any OpenAI SDK with base_url https://api.runinfra.ai/v1 (POST /chat/completions) or an Anthropic SDK against POST /v1/messages, with a workspace key as Bearer or x-api-key; list model IDs with GET /v1/models (needs the key); coding-agent setup via `npx -y @runinfra/cli@latest` and https://runinfra.ai/docs/tools-sdks/agent-setup.md.
  • Check each model's own license before shipping its outputs in a product
  • Read Retry-After / Retry-After-Ms on 429 instead of hard-coded backoff
  • Agent setup spends real credits; show the plan and get the user's yes before installing or changing agent settings

llms.txt: runinfra.ai/llms.txt · MCP: https://runinfra.ai/docs/mcp (docs search only, HTTP, no auth)

Paste into your agent: Read https://agentgid.com/resources/runinfra/agent.md before using RunInfra.

Quick answers

Does RunInfra have an API?

Yes. RunInfra has an official API documented at https://runinfra.ai/docs/api-reference/model-apis-quickstart.

Does the RunInfra API need a key?

Yes, you need an API key. Limits: Per-key requests per minute: 10,000 before the first credit purchase, 50,000 after; tokens-per-minute tier per model grows with lifetime purchases; every 429 carries Retry-After

Is RunInfra free?

Yes, there is a free tier: $1 credit once on signup (never expires); then pay-as-you-go top-ups from $5, per-token prices per model Paid plans start at $10 a month.

Can I use RunInfra in a commercial project?

Yes. Its terms say: "You own the outputs generated by your deployed pipelines. We do not use your API inputs or outputs to train any models or for any purpose other than providing the Services."

What you can build

  • A coding-agent setup that routes cheap background tasks to an open model through the Anthropic-compatible endpoint
  • A cost comparison harness that runs the same prompts against several open models with one SDK
  • A JSON-extraction service on an open model with tool calling and JSON mode

Alternatives in Model APIs and gateways

All 7 →

Zro You can point an existing coding agent at cheaper open models by changing a base URL, without request bodies being stored or used for training. API (paid)Commercial OK Cohesor You can cut and cap agent model spend by swapping one base URL and key instead of rewriting code for each provider. API (paid)Commercial OK LLMTest A provider outage or a reply that is not valid JSON no longer breaks your feature, because the proxy retries on another model inside the same request, and you see what each AI feature costs. API (paid)Commercial OK Nous Research (Nous Portal inference API) You can call Hermes models through a standard OpenAI client, or download the same weights from Hugging Face and run them yourself. APIDownloadFree tierCommercial: conditions Tokenwise You find out which prompts and models drive your LLM bill by changing one base URL, while your own provider keys pass through and are not stored. API (paid)Free tierCommercial OK Opper AI Switching or pooling model providers becomes a model-string change, and teams that must keep data in the EU get one sub-processor and one DPA instead of a contract per provider. APIFree tierCommercial OK

Something wrong or out of date? Tell us.