# Unify

**Canonical:** https://apis.io/providers/unify-ai/  
**Website:** https://unify.ai  
**APIs profiled:** 8

Unify is an LLM routing and model gateway platform that enables developers to access 100+ large language model providers through a single unified REST API and API key. The platform dynamically routes each prompt to the optimal model based on user-defined preferences across quality, speed, and cost dimensions, using live runtime benchmarks updated continuously across providers including OpenAI, Anthropic, Mistral, Together AI, Replicate, Groq, DeepSeek, and many more. Unify provides an observability dashboard for comparing model and provider performance, automatic fallback routing, and caching capabilities to reduce redundant API calls. Developers can benchmark models on their own prompts using standardized datasets and switch providers without rewriting application code using the unified model@provider endpoint syntax.

## Kin Score — 52.1 / 100 (developing)

Scored 2026-08-25 under rubric 0.14.0. Trend: flat (+0.0 from 52.1).

| Facet | Score |
|---|---|
| Discoverability | 74.1 |
| Contract Quality | 70.1 |
| Governance | 25.0 |
| Contract Governance | 25.0 |
| Operational Transparency | 52.6 |
| Developer Ergonomics | 28.6 |
| Commercial Clarity | 57.9 |
| Access Clarity | 57.9 |

## Agent readiness — 21.5 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | documented |
| MCP Server | no |
| Auth Clarity | bearer |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | documented |
| Event Surface Described | no |
| Agent Skills | no |
| 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 |

## Access

Freemium · Self-serve signup — onboarding: self-serve, pricing: freemium, trial: no (confidence: high).

## APIs (8)

- **Unify Agent API** — Send messages to and retrieve messages from assistants
- **Unify Assistants API** — Create and manage AI assistants within your workspace
- **Unify Contexts API** — Named sub-collections of logs within a project
- **Unify Logs API** — Structured logging — create, query, derive, and manage log entries
- **Unify Organizations API** — Multi-user organization management
- **Unify Platform API** — Platform-level utilities including credits and user info
- **Unify Projects API** — Create and manage projects for organizing logs and contexts
- **Unify Spaces API** — Collaboration spaces for grouping assistants

## Agentic access (1)

- **Unify Ai Agentic Access** — 48 operations · 33 acting

## Security (4)

- **Unify Ai Authentication** — http · 1 scheme
- **Unify Ai Domain Security** — TLSv1.3 · HSTS · DNSSEC · DMARC
- **Unify Ai Vulnerability Disclosure** — disclosure policy published
- **Unify Ai Trust Center** — SOC 2, ISO 27001, GDPR

## Plans (1)

- **Unify Ai Plans Pricing**

## Tags

LLM, Artificial Intelligence, Large Language Models, LLM Routing, Model Gateway, AI Gateway, OpenAI, Anthropic, Mistral, Benchmarking, Model Comparison, AI Infrastructure, Machine-Learning

---

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