# 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.

- Category: Model APIs and gateways · by RightNow AI, Inc.
- Website: https://runinfra.ai/
- Live data: no
- Checked on the official pages: 2026-10-24

## API

- Official API: yes, docs https://runinfra.ai/docs/api-reference/model-apis-quickstart
- Key needed: yes
- Price: Paid; 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
- Base URL: https://api.runinfra.ai/v1
- Formats: json

## Price and code

- Free tier: $1 credit once on signup (never expires); then pay-as-you-go top-ups from $5, per-token prices per model; paid from $10/month (https://runinfra.ai/pricing)

## Data and license

- License: RunInfra Legal Terms (RightNow AI, Inc.) (https://runinfra.ai/terms-of-service); covers 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 OK
- Credit: not stated
- Embedding unclear
- Quote (api_official): "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." (https://runinfra.ai/llms.txt)
- Quote (api_key): "The endpoint needs a workspace API key, sent as `Authorization: Bearer` or `x-api-key`." (https://runinfra.ai/docs/api-reference/models.md)
- Quote (api_price): "Pay as you go: Model API usage is billed per token at each model's published input, cached-input where configured, and output prices." (https://runinfra.ai/llms.txt)
- Quote (free_tier): "Free on signup | $1, once per account, never expires" (https://runinfra.ai/docs/introduction/plans.md)
- Quote (paid_from): "Starter: $10 a month. About $12 of usage a month, paced as $2.77 a week and $1.11 per 5 hours." (https://runinfra.ai/llms.txt)
- Quote (limits): "Requests per minute, per API key. The default is 10,000 before your first credit purchase and 50,000 after it." (https://runinfra.ai/docs/introduction/plans.md)
- Quote (commercial): "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." (https://runinfra.ai/terms-of-service)
- Quote (model_licenses): "Your use of these models is subject to their respective licenses (e.g., Apache 2.0, MIT, Llama Community License)." (https://runinfra.ai/terms-of-service)
- Quote (resale): "Use the Services to generate revenue through reselling GPU access without authorization" (https://runinfra.ai/terms-of-service)
- Quote (maker): "We are RightNow AI, Inc. ("Company," "we," "us," "our"), a company registered in Delaware, United States" (https://runinfra.ai/terms-of-service)
- Quote (mcp): ""name":"RunInfra Docs MCP","description":"Search and retrieve RunInfra documentation"" (https://runinfra.ai/docs/.well-known/mcp/server-card.json)

## Rules for an 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

## Agent access

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

Human page: https://agentgid.com/resources/runinfra/
Source: AgentGid (agentgid.com). Facts are quoted from the site's own pages; check the license page before you ship.