LLM gateways compared
Every gateway we hold a catalog for, side by side: how many models it carries,
how many it publishes prices for, and when we last checked. Counts come from each
gateway's own /models endpoint.
| Gateway | Status | Models | Text / multimodal | With pricing | Max context | Last checked |
|---|---|---|---|---|---|---|
| OpenRouter The reference catalog for unified LLM access. | Live | 452 | 436 | 445 | 2M | |
| Vercel AI Gateway Vercel's gateway, wired into the AI SDK. | Live | 498 | 334 | 419 | 2M | |
| Cloudflare AI Gateway Edge gateway in front of Workers AI and third-party providers. | Live | 1,982 | 572 | — | — | |
| OrcaRouter Unified routing with an automatic model picker. | Live | 214 | 170 | 188 | 1.1M | |
| Requesty Routing policies, caching, and guardrails. | Live | 629 | 625 | 629 | 2M | |
| Concentrate Unified gateway with a bare-id catalog. | Live | 208 | 207 | — | 1.1M | |
| LLM Gateway Open-source, self-hostable, AGPLv3. | Live | 288 | 206 | 288 | 2M | |
| Baseten Dedicated inference for open-weight models. | Live | 20 | 20 | 20 | 1M | |
| Darkbloom Compact OpenAI-compatible gateway. | Live | 12 | 12 | 12 | 1M | |
| Ramp Router Ramp’s cost-optimized model router. | Live | 109 | 109 | 109 | 1.1M | |
| Together AI Open-model inference at scale. | Live | 82 | 23 | 82 | 1M | |
| Sail Efficiency-tuned inference for open models. | Live | 10 | 8 | — | — | |
| Fireworks AI Fast serving and fine-tuning for open models. | Crawl failing | 20 | 18 | — | 1M | |
| Morph Fast open models and code-editing models on a custom inference stack. | Live | 14 | 10 | 9 | 1M | |
| Cheaper Inference A discount marketplace for frontier and open models. | Live | 570 | 376 | 570 | 2M | |
| SayGM A privacy-first gateway with confidential (TEE) model variants. | Live | 45 | 45 | 45 | — | |
| Experiential Labs An open-source gateway with per-model provider waterfalls. | Live | 275 | 264 | 265 | 1.3M | |
| NanoGPT A large multi-vendor catalog on an OpenAI-compatible API. | Live | 625 | 624 | 623 | 10M | |
| Isoquant A small curated catalog with zero-data-retention routing. | Live | 3 | 3 | 3 | 1M | |
| Celeris | Live | 2 | 2 | 2 | 131.1K | |
| TypeSafe | Key storage only | — | — | — | — | — |
| OpenAI | Key storage only | — | — | — | — | — |
Models counts every id in the gateway's catalog, including image, video, and embedding models. Text / multimodal narrows that to models that take a prompt and return text. With pricing is how many of them the gateway publishes a token price for — the rest are served but unpriced in its public catalog.
Tracked, not integrated
Gateways without a catalog here
These are real, notable gateways that FreeRouter does not crawl yet, so we have no model data for them. They are listed for completeness and carry no invented numbers.