# Apertis AI — Full Service Description

> Model Supply & Delivery Infrastructure for AI Agents: model access and delivery for AI agents and AI apps through OpenAI-compatible routing, budgets, model policy, and failover.

## About

Apertis AI is model supply and delivery infrastructure for teams that run AI agents and AI applications. It provides one OpenAI-compatible gateway for routing requests across 500+ models and 30+ providers while adding operational controls such as virtual keys, budgets, model policy, routing health, and automatic failover.

Apertis AI is operated by STIMA AI LLC.

The primary brand position is model supply and delivery for AI agents and AI applications. Spend control (budgets, spend caps, quotas, scoped keys) is a delivery capability, not the category. Model breadth is supporting proof: Apertis keeps access broad while giving teams a central place to govern spend, provider choice, and rollout behavior.

## Who Apertis Serves

- Engineering teams standardizing access for coding agents and AI tools
- Platform teams that need centralized model policy and budget controls
- Developers migrating OpenAI-compatible applications to a multi-provider gateway
- Teams comparing provider cost, context windows, routing health, and failover options
- Organizations that want a managed alternative to self-hosted routing infrastructure

## Delivery Capabilities

### Virtual Keys

Teams can issue controlled API keys for applications, environments, users, and coding agents. This gives operators a way to separate usage, rotate access, and connect spend to the right workflow.

### Budgets And Usage Controls

Apertis supports budget-aware rollout for AI applications and coding tools. Teams can track usage, compare costs, and prevent uncontrolled agent spend from spreading across unmanaged provider accounts.

### Model Policy

Model policy helps teams decide which models and providers are available for a workflow. It supports governed access without forcing application code to understand every upstream provider.

### Routing Health And Failover

Requests can route through available provider channels, with automatic failover when a primary channel is unavailable. This improves reliability for coding agents and production AI apps.

### Provider Cache Pricing

When an upstream provider caches part of a prompt, PAYG settlement reads its cache counters from the upstream response and applies the shared model/provider resolver; omitted counters are not inferred from request content. Because one model can reach several routes, Apertis publishes a cache multiplier only when it is attributable to that model or a measured route; otherwise the model detail page reports the rate as not published.

### Model And Provider Coverage

Apertis provides routed access to 500+ models from 30+ providers, including OpenAI, Anthropic, Google, AWS Bedrock, Azure OpenAI, Mistral, Cohere, DeepSeek, SpaceXAI, Alibaba/Qwen, Baidu, Tencent, Zhipu, Cloudflare Workers AI, and more.

## API Endpoints

All API endpoints require an Apertis API key sent as a Bearer token.

### Base URL

```text
https://api.apertis.ai/v1
```

### Text Generation

- `POST /v1/chat/completions` — OpenAI-compatible chat completions for frontier, open, and provider-hosted models.
- `POST /v1/completions` — Legacy text completions for compatible models.
- `POST /v1/messages` — Native Anthropic Messages API format for Anthropic-style clients.

### Other Modalities

- `POST /v1/embeddings` — Text embedding generation.
- `POST /v1/images/generations` — Image generation through supported image models.
- `POST /v1/audio/speech` — Text-to-speech.
- `POST /v1/audio/transcriptions` — Speech-to-text.
- `POST /v1/audio/translations` — Audio translation.
- `POST /v1/moderations` — Content moderation through supported moderation models.

### Models

- `GET /v1/models` — List available models.
- `GET /v1/models/:model` — Get model details.

## Integration Pattern

Apertis is compatible with the OpenAI SDK pattern. Existing applications usually change the API key and base URL while keeping the same request shape.

```python
from openai import OpenAI

client = OpenAI(
    api_key="your-apertis-key",
    base_url="https://api.apertis.ai/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    messages=[{"role": "user", "content": "Hello"}],
)
```

## Web Search Suffix

When enabled for an account and model, adding `:web` to a model ID can trigger web-search augmentation:

```python
response = client.chat.completions.create(
    model="gpt-4o-mini:web",
    messages=[{"role": "user", "content": "Summarize today's AI infra news"}],
)
```

## Pricing And Plans

- Pay-as-you-go: no monthly fee; pay based on usage.
- Coding Plan Lite: monthly plan for individual developer workflows.
- Coding Plan Pro: higher quota plan for power users and frequent coding-agent usage.
- Coding Plan Plus: expanded quota plan for sustained coding-agent workloads.
- Coding Plan Max: larger plan for teams and heavier agent workloads.
- Enterprise pilot: managed Team Gateway rollout for organizations that need central controls and support.

All plans can use the Apertis gateway capabilities available to the account, including model routing and failover.

## SDK And Tool Integrations

- OpenAI Python SDK: compatible through base URL and API key changes.
- OpenAI JavaScript SDK: compatible through base URL and API key changes.
- Vercel AI SDK: Apertis provider support.
- LiteLLM: supported as a proxy target.
- LlamaIndex: supported integration.
- Kilo Code: supported provider workflow.
- MCP: Apertis MCP server metadata is available for agent clients.

## Compatible Coding Tools

- Claude Code
- Cursor
- OpenCode
- Aider
- Cline
- Continue
- Kilo Code

## Authoritative Discovery Files

- [llms.txt](https://apertis.ai/llms.txt): concise AI-facing site summary.
- [Homepage Markdown](https://apertis.ai/homepage.md): machine-readable mirror of the canonical homepage narrative and links.
- [Japanese Homepage Markdown](https://apertis.ai/ja/homepage.md): machine-readable mirror of the Japanese homepage.
- [Changelog Markdown](https://apertis.ai/changelog.md): machine-readable mirror of the release index; per-release mirrors at https://apertis.ai/changelog/{version}.md.
- [OpenAPI Description](https://apertis.ai/docs/openapi.yaml): machine-readable API description.
- [API Catalog](https://apertis.ai/.well-known/api-catalog): API discovery metadata.
- [Agent Skills Index](https://apertis.ai/.well-known/agent-skills/index.json): agent-facing skills index.
- [MCP Server Card](https://apertis.ai/.well-known/mcp/server-card.json): MCP server metadata.
- [Sitemap](https://apertis.ai/sitemap.xml): canonical public URL map.
- [Robots](https://apertis.ai/robots.txt): crawler and content-signal policy.

## Core Pages

- [Homepage](https://apertis.ai/): model supply and delivery positioning, hero overview, supported providers, and pilot CTA.
- [Models](https://apertis.ai/models): searchable model catalog with pricing, providers, context windows, and feature metadata.
- [Japanese Homepage](https://apertis.ai/ja): Japanese-language homepage carrying the same product facts as the English root.
- [Japanese Models](https://apertis.ai/ja/models): Japanese-language model catalog with the same data as /models.
- [Helmway](https://apertis.ai/helmway): source-grounded document intelligence for PDFs, scanned files, spreadsheets, and Office docs with exact evidence anchors.
- [Pricing](https://apertis.ai/subscribe): Coding Plan and pay-as-you-go information.
- [Enterprise](https://apertis.ai/enterprise): Team Control pilots for multi-SDK agent routing, budgets, model policy, and failover, on one Apertis bill. Markdown: https://apertis.ai/enterprise.md
- [Enterprise Pilot](https://apertis.ai/enterprise/form): contact form for Team Control pilots; reviewed manually and answered by email within one business day. Markdown: https://apertis.ai/enterprise/form.md
- [Changelog](https://apertis.ai/changelog): product updates, model additions, and release notes.
- [Cost Calculator](https://apertis.ai/calculator): usage and cost comparison tool.
- [Cost Calculator Markdown](https://apertis.ai/calculator.md): machine-readable mirror of the curated model set with Apertis and market list rates per 1M tokens.
- [Platform Comparisons](https://apertis.ai/compare): Index of Apertis decision pages against other model-access platforms. Markdown: https://apertis.ai/compare.md
- [Apertis vs OpenRouter](https://apertis.ai/compare/openrouter): Governed workspace versus multi-provider routing marketplace. Markdown: https://apertis.ai/compare/openrouter.md
- [Apertis vs Together AI](https://apertis.ai/compare/together-ai): Governed multi-provider gateway versus an inference and deployment platform. Markdown: https://apertis.ai/compare/together-ai.md
- [Apertis vs LiteLLM](https://apertis.ai/compare/litellm): Managed gateway workspace versus a self-operated proxy. Markdown: https://apertis.ai/compare/litellm.md
- [Model Comparison](https://apertis.ai/models/compare): side-by-side model comparison.
- [Academic Research Programme](https://apertis.ai/academic): $50 in free credits for academic researchers, with one OpenAI-compatible key across 500+ models. Markdown: https://apertis.ai/academic.md
- [Academic Application](https://apertis.ai/academic/apply): apply for academic access; reviewed manually and answered by email within 48 hours. Markdown: https://apertis.ai/academic/apply.md
- [Integrations Index](https://apertis.ai/integrations): setup guides for coding agents, all pointed at the one OpenAI-compatible endpoint, with the activation check each guide ends on. Markdown: https://apertis.ai/integrations.md
- [OpenCode Setup](https://apertis.ai/integrations/opencode): configure an OpenAI-compatible custom provider in opencode.json. Markdown: https://apertis.ai/integrations/opencode.md
- [Kilo Code Setup](https://apertis.ai/integrations/kilo): add Apertis as a custom provider and load current model IDs. Markdown: https://apertis.ai/integrations/kilo.md
- [Cline Setup](https://apertis.ai/integrations/cline): set the OpenAI-compatible provider, base URL, key, and model ID in Cline. Markdown: https://apertis.ai/integrations/cline.md
- [Roo Code Setup](https://apertis.ai/integrations/roocode): point Roo Code at the Apertis OpenAI-compatible endpoint. Markdown: https://apertis.ai/integrations/roocode.md
- [LiteLLM Setup](https://apertis.ai/integrations/litellm): add Apertis as a LiteLLM Proxy upstream with LiteLLM's built-in apertis provider, keeping the local endpoint your OpenAI and Anthropic SDK clients already call. Markdown: https://apertis.ai/integrations/litellm.md
- [Codex Setup](https://apertis.ai/integrations/codex): add Apertis as a custom model provider in Codex config.toml using the Responses wire API. Markdown: https://apertis.ai/integrations/codex.md

## Comparison Pages

- [Apertis vs OpenRouter](https://apertis.ai/compare/openrouter): comparison of managed routing, model coverage, and workflow fit.
- [Apertis vs Together AI](https://apertis.ai/compare/together-ai): comparison with Together AI.
- [Apertis vs LiteLLM](https://apertis.ai/compare/litellm): comparison with self-hosted proxy infrastructure.

## Trust, Privacy, And Legal

- Apertis does not train models on user data.
- Requests are routed to upstream providers according to provider and account configuration.
- TLS is used for data in transit.
- API keys are protected in storage.
- [Trust Center](https://apertis.ai/trust): security controls, data handling, compliance posture, and subprocessors.
- [Trust Center Markdown](https://apertis.ai/trust.md): machine-readable mirror of the Trust Center.
- [Request a DPA or HIPAA BAA](https://apertis.ai/trust/dpa): request form for a Data Processing Agreement or a HIPAA Business Associate Agreement.
- [DPA and HIPAA BAA Markdown](https://apertis.ai/trust/dpa.md): machine-readable mirror of the DPA and HIPAA BAA request information.
- [Terms of Service](https://apertis.ai/terms): the contract governing use of Apertis.
- [Terms of Service Markdown](https://apertis.ai/terms.md): machine-readable mirror of the English Terms of Service.
- [Japanese Terms of Service](https://apertis.ai/ja/terms): Japanese version of the contract governing use of Apertis.
- [Japanese Terms of Service Markdown](https://apertis.ai/ja/terms.md): machine-readable mirror of the Japanese Terms of Service.
- [Privacy Policy](https://apertis.ai/privacy): what is collected, how it is used, how long it is kept, and who processes it.
- [Privacy Policy Markdown](https://apertis.ai/privacy.md): machine-readable mirror of the English Privacy Policy.
- [Japanese Privacy Policy](https://apertis.ai/ja/privacy): Japanese version of the Privacy Policy.
- [Japanese Privacy Policy Markdown](https://apertis.ai/ja/privacy.md): machine-readable mirror of the Japanese Privacy Policy.
- [Refund Policy](https://apertis.ai/refund): refund and cancellation terms.
- [Refund Policy Markdown](https://apertis.ai/refund.md): machine-readable mirror of the English Refund Policy.
- [Japanese Refund Policy](https://apertis.ai/ja/refund): Japanese version of the Refund Policy.
- [Japanese Refund Policy Markdown](https://apertis.ai/ja/refund.md): machine-readable mirror of the Japanese Refund Policy.
- [GitHub Promotion Policy](https://apertis.ai/github-promotion-policy): rules for the GitHub promotion rewards program.
- [GitHub Promotion Policy Markdown](https://apertis.ai/github-promotion-policy.md): machine-readable mirror of the English GitHub Promotion Policy.
- [Japanese GitHub Promotion Policy](https://apertis.ai/ja/github-promotion-policy): Japanese version of the GitHub Promotion Policy.
- [Japanese GitHub Promotion Policy Markdown](https://apertis.ai/ja/github-promotion-policy.md): machine-readable mirror of the Japanese GitHub Promotion Policy.
- Each document states its own effective date on the page; the bare path always serves the version in force.
- Superseded versions remain accessible from the current page's version menu, carry `noindex`, and are intentionally omitted from the sitemap.

## Contact

- Website: https://apertis.ai
- Email: hi@apertis.ai
- Status: https://status.apertis.ai
- GitHub: https://github.com/apertis-ai
- API docs: https://docs.apertis.ai
- Terms: https://apertis.ai/terms
- Privacy: https://apertis.ai/privacy