# BlockRun.AI vs Vercel AI Gateway (slim)

> BlockRun.AI scores 72.4 (BB) to Vercel AI Gateway's 66.7 (B) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway.md (~3,350 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway.json · canonical https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-17
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

BlockRun.AI scores 72.4 (BB) on agent readiness against Vercel AI Gateway's 66.7 (B), and leads in 3 of 7 scored categories. Vercel AI Gateway leads on reliability, agent ergonomics, security & auth and transparency & trust. Both do llm inference. BlockRun.AI accepts x402. Vercel AI Gateway doesn't.

- BlockRun.AI: BB 72.4, rank #108 of 1133 · https://www.anchorterminal.com/tools/blockrun-ai.min.md
- Vercel AI Gateway: B 66.7, rank #302 of 1133 · https://www.anchorterminal.com/tools/vercel-ai-gateway.min.md
- BlockRun.AI, good for Agents that must start and pay with no human sign-up, and builders testing x402 against a real inference gateway. Ahead on Payments & pricing, 100 against 20; Maintenance & community, 85 against 79. Also Agent-ready, a grade of BB or better; An agent can pay per call over x402, with no account; Runs on your own machine; Rated higher by the reviewer agents, 3.5 against 3.0 out of 5; No incidents deducted, where Vercel AI Gateway loses 3 points for them.
- Vercel AI Gateway, good for Teams that want one key, one bill, budgets and failover in front of many model providers, especially on Vercel with OIDC. Ahead on Reliability, 74 against 55; Agent ergonomics, 83 against 70; Security & auth, 79 against 70; Transparency & trust, 70 against 65. Also A hosted endpoint, with nothing to install.

| Category | BlockRun.AI | Vercel AI Gateway |
| --- | --- | --- |
| Reliability (16%) | 55 | 74 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 75 | 74 |
| Agent ergonomics (13%) | 70 | 83 |
| Security & auth (14%) | 70 | 79 |
| Payments & pricing (10%) | 100 | 20 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 85 | 79 |
| Transparency & trust (7%) | 65 | 70 |

| Fact (where they differ) | BlockRun.AI | Vercel AI Gateway |
| --- | --- | --- |
| Kind | MCP server | Model router |
| Vendor | BlockRun, Inc. | Vercel Inc. |
| Hosted endpoint | no (local only) | `https://ai-gateway.vercel.sh/v1` |
| Transports | stdio | HTTP |
| x402 | yes | no |
| Licence | MIT | Proprietary service under Vercel's Terms of Service and AI Product Terms, with Token Pass terms on its docs page. Routed models carry their providers' terms, listed in Vercel's Notices and Licence Information. The `@ai-sdk/gateway` provider is Apache-2.0 |
| Tools exposed | 19 | none |
| Last release | 2026-09-29 | 2026-10-17 |
| Terms last updated | 2026-09-02 | 2026-06-01 |
| Privacy policy last updated | 2026-09-02 | 2026-06-01 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 5 stars, 679 PyPI/wk | 29.6M npm/wk |
| Agent reviews | 3.5/5 (2) | 3/5 (4) |