Unify
"Dynamically routes each prompt to the best LLM and provider so you can balance quality, speed, and cost with ease. Access all LLMs across all providers with a single API key and a standard API." [1]
Unify is an LLM routing gateway that lets developers access models from multiple providers through a single API key, dynamically selecting the best model per prompt to balance quality, speed, and cost. It is aimed at teams that need provider-level failover, observability, spend controls, and benchmarking across LLMs. Pricing starts at $75 per month with a self-serve signup and free starter credits; an enterprise plan with on-premises deployment is available through sales. The platform is GDPR compliant, with SOC 2 Type II and ISO 27001 certifications in progress.
Best for / Avoid if
Best for: Prototypes and side projects - free to start, no sales call; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box
Pricing & procurement
- Pricing model
- Hybrid (base + usage) [2]
- Published pricing
- ✓ Yes
- Free tier
- ✓ Yes [3]
- Free tier details
- Developer (free) plan: unlimited interfaces, 1K LLM queries/month, 5K logs/month, individual user account. Self-serve signup, no credit card required. [4]
- Self-serve signup
- ✓ Yes [5]
- Requires sales call
- ✗ No
- Enterprise plan
- ✓ Yes [6]
| Plan | Item | Per | Amount | Source |
|---|---|---|---|---|
| Developer | LLM gateway access | month | $0 | source |
| Professional | LLM gateway access per seat | seat/month | $40 | source |
| Enterprise | LLM gateway access (custom) | - | source |
Capabilities
- Supported actions
- unified_chat_completions, model_routing, automatic_fallback, observability_logging, tracing, benchmarking, custom_routing_rules, spend_limits, rate_limiting, byo_provider_keys, on_premises_deployment
- Input types
- chat completions, text completions
- Output types
- streaming (SSE), JSON
- Webhooks
- – Unknown
- Sandbox / test mode
- ✗ No [7]
- SDK languages
- Python [8]
- MCP server
- ✗ No [9]
Trust & compliance
- SOC 2
- In progress [10]
- HIPAA
- ✗ No [11]
- GDPR
- ✓ Yes [12]
- ISO 27001
- ✗ No [13]
- PCI DSS
- ✗ No [14]
- Published SLA
- ✗ No [15]
- Known restrictions
- Free tier limited to 1K LLM queries/month and 5K logs/month, Professional plan capped at 10 seats per team, Enterprise on-premises deployment requires sales contact, The primary unify.ai domain now hosts 'Droid', a separate AI agent/teammate platform; the original LLM gateway product is maintained at landing.unify.ai, SOC 2 Type II audit in progress; Type I attestation in place, ISO 27001 certification in progress, not yet certified [16]
Developer surface
Integration
- API style
- rest
- Base URL
- https://api.unify.ai/v0
- Version
- v0
- Versioning
- url
- Stability
- ga
- Auth methods
- api_key
- Error format
- vendor-specific
- Python
unifyai· repo
Adoption & maturity
- Launched
- 2023-01-01
- GA
- 2024-05-22
Other AI Gateway & LLM Routing APIs
Vercel AI Gateway
"AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks."
Portkey
"Production Stack for Gen AI Builders"
Bifrost (Maxim AI)
"The fastest, most resilient, enterprise-grade LLM, MCP, and agent gateway."
Cloudflare AI Gateway
"Connect to any model, dynamically route requests, and manage usage, billing, and logs from one unified gateway."
TrueFoundry AI Gateway
"A unified AI gateway to securely manage and govern AI across 1600+ models with policy control, real-time monitoring, and up to 30% cost reduction."
Helicone
"Open-source LLM observability and monitoring platform for developers" - routes, debugs, and analyzes AI applications with access to 100+ models through one API with built-in observability, automatic fallbacks, and zero markup pricing.
References
- ↑Description: landing.unify.ai · ycombinator.com
- ↑Pricing model: landing.unify.ai
- ↑Free tier: landing.unify.ai
- ↑Free tier details: landing.unify.ai
- ↑Self-serve signup: landing.unify.ai
- ↑Enterprise plan: landing.unify.ai
- ↑Sandbox: landing.unify.ai
- ↑SDK languages: github.com · sourceforge.net
- ↑MCP server: unify.ai
- ↑SOC 2: usedroids.ai · unify.ai
- ↑HIPAA: usedroids.ai · unify.ai
- ↑GDPR: unify.ai · landing.unify.ai
- ↑ISO 27001: usedroids.ai · unify.ai
- ↑PCI DSS: usedroids.ai · unify.ai
- ↑Published SLA: usedroids.ai · unify.ai
- ↑Known restrictions: unify.ai · landing.unify.ai
Change history
- 2026-06-21 Capabilities: {} → {"self_hosted":true,"observability":true,"spend_controls":true,"fallback_routin…
- 2026-06-21 Summary Md: (none) → Unify is an LLM routing gateway that lets developers access models from multipl…
- 2026-06-21 Score Pricing Transparency: (none) → 100
- 2026-06-21 Score Agent Friendliness: (none) → 35
- 2026-06-21 Score Setup Speed: (none) → 75
- 2026-06-21 Score Docs Quality: (none) → 25
- 2026-06-21 Score Procurement Friction: (none) → 100
- 2026-06-21 Score Trust Readiness: (none) → 23
- 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, AI agents and auto…
- 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-21 Has Structured Data: (none) → No
- 2026-06-21 Robots Allows Agents: (none) → Yes
- 2026-06-21 Status Page URL: (none) → https://status.unify.ai
- 2026-06-21 Docs URL: (none) → https://docs.unify.ai/basics/overview
- 2026-06-21 Llms Txt URL: (none) → https://unify.ai/llms.txt
- 2026-06-21 Llms Txt Present: (none) → Yes
- 2026-06-21 Rendering: (none) → static
- 2026-06-21 Free Tier Available: set to Yes
- 2026-06-21 Free Tier Details: set to Developer (free) plan: unlimited interfaces, 1K LLM queries/month, 5K logs/mont…
- 2026-06-21 Self Serve Signup: set to Yes
- 2026-06-21 Requires Sales Call: set to No
- 2026-06-21 Enterprise Plan Available: set to Yes
- 2026-06-21 SOC 2: set to in_progress
- 2026-06-21 HIPAA: set to No
- 2026-06-21 GDPR: set to Yes
- 2026-06-21 ISO 27001: set to No
- 2026-06-21 PCI DSS: set to No
- 2026-06-21 SLA Published: set to No
- 2026-06-21 Data Retention Policy URL: set to https://unify.ai/privacy-policy
- 2026-06-21 Known Restrictions: set to Free tier limited to 1K LLM queries/month and 5K logs/month, Professional plan …
- 2026-06-21 Auth Methods: set to api_key
- 2026-06-21 Auth Docs URL: set to https://docs.unify.ai/basics/welcome
- 2026-06-21 API Style: set to rest
- 2026-06-21 Base URL: set to https://api.unify.ai/v0
- 2026-06-21 API Version: set to v0
- 2026-06-21 Versioning Scheme: set to url
- 2026-06-21 Stability: set to ga
- 2026-06-21 Quickstart URL: set to https://docs.unify.ai/basics/quickstart
- 2026-06-21 Error Format: set to vendor-specific
- 2026-06-21 Requires Verification: set to No
- 2026-06-21 Starting Price Usd: set to 75
- 2026-06-21 Price Basis: set to month
- 2026-06-21 Slug: set to unify
- 2026-06-21 Launched At: set to 2023-01-01
- 2026-06-21 GA Date: set to 2024-05-22
- 2026-06-21 Notable Customers: set to (none)
- 2026-06-21 Fields Not Found: set to documented_rate_limits, sla_published, webhooks_supported, mcp_server_available…
- 2026-06-21 Source Confidence: set to high
- 2026-06-21 Extractor: set to claude-subagent:sonnet
- 2026-06-21 Last Verified At: set to 2026-06-21T00:00:00.000Z
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/unify \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/unify/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'