Verified 2026-11-18 · rates follow the live catalog
OpenRouter is the widest model marketplace: 600+ models from 80+ providers behind one OpenAI-compatible API. Inference is billed at each provider's list price, and OpenRouter's own fee is charged when you buy credits — 5.5% on Standard, 8% on Business. Openference is deliberately narrower: a curated catalog, with plans that bundle usage into one monthly price. Pick OpenRouter when breadth and per-provider routing matter most; pick Openference when you want a flat monthly price and a catalog that is already vetted.
Hosted gateway · Pay-as-you-go + 5.5% credit fee · Checked 19 November 2026 against OpenRouter Pricing.
Pick OpenRouter for the widest model choice and routing control. Pick Openference for a predictable monthly price and a curated catalog.
| Plan | Price | What it includes |
|---|---|---|
| Free | $0 | 25+ free models. 50 requests per day, rising to 1,000 per day once you have bought at least $10 of credits. Community support. |
| Standard | 5.5% credit fee | Pay-as-you-go credits at provider list price across 600+ models. Budgets, prompt caching, auto-routing and a management API key. Email support. |
| Business | 8% credit fee | Standard, plus EU and US in-region routing, workload identity federation and up to 1,000 workspaces. |
| Enterprise | Contact sales | SSO/SAML, contractual SLAs, invoicing and discounted platform fees, with a dedicated support team. |
| OpenRouter | Openference | |
|---|---|---|
| Pricing model | Pay-as-you-go credits | Plan-based (included usage) + on-demand credits |
| Fee on top of model rates | 5.5% on credit purchases (Standard), 8% (Business) | No per-request fee and no markup on listed rates; 5% processing fee on credit top-ups |
| Models included | 600+ models from 80+ providers | Curated open and frontier catalog |
| Open-weight models | Yes | Yes |
| Proprietary frontier models | Yes | Yes |
| Automatic failover across providers | Yes — provider and model fallback routing | Yes |
| Team features | Workspaces on every plan; SSO/SAML on Enterprise only | Teams from $30/seat with per-seat allowances |
Pay-as-you-go + 5.5% credit fee. The plan table above lists each tier as OpenRouter publishes it, read from OpenRouter Pricing on 19 November 2026.
That depends on how you use it. Pick OpenRouter for the widest model choice and routing control. Pick Openference for a predictable monthly price and a curated catalog.
OpenRouter's from its own pages on 19 November 2026; Openference's from its live catalog and public plans. Both change, so confirm on the linked page before you commit.
More on the comparison index, the current plans and the model catalog.
Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API