# ToAPIs

**Canonical:** https://apis.io/providers/toapis/  
**Website:** https://toapis.com  
**APIs profiled:** 1

An OpenAI-compatible AI API gateway/aggregator fronting 50+ text, image, and video models (GPT, Claude, Gemini, DeepSeek, Qwen, Sora/Veo/Kling, etc.) behind a single integration, with model routing, provider failover, unified usage tracking, and consolidated billing.

## Kin Score — 43.7 / 100 (developing)

Scored 2026-09-07 under rubric 0.20.0.

| Facet | Score |
|---|---|
| Discoverability | 70.4 |
| Contract Quality | 41.6 |
| Governance | 18.2 |
| Contract Governance | 18.2 |
| Operational Transparency | 42.1 |
| Developer Ergonomics | 54.8 |
| Commercial Clarity | 38.2 |
| Access Clarity | 38.2 |

## Agent readiness — 32.2 (agent-ready)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | documented |
| Auth Clarity | bearer |
| Idempotency | no |
| Error Semantics | documented |
| OpenAPI Examples | no |
| Rate Limit Signal | documented |
| Event Surface Described | yes |
| Agent Skills | yes |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |

## APIs (1)

- **ToAPIs API** — OpenAI-compatible REST API covering chat/completions, image generation, video generation, and model listing (plus Anthropic Messages and OpenAI Responses formats). Key-authentic...

## MCP servers (1)

- **ToAPIs MCP Server**

## Security (2)

- **Toapis Authentication** — 1 scheme
- **Toapis Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Toapis Plans Pricing**

## Tags

AI API, LLM/AI gateway, model aggregation, OpenAI-compatible, model routing, provider failover, text generation, image generation, video generation, developer tools

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/toapis/). Scores are computed from the provider's own public artifacts under a published rubric.