Models ranked by cost x context efficiency; the formula ships with each row.
| Paid endpoint | Price / call | Parameters |
|---|---|---|
| best_under_budget Ask "which LLM gives the best value for the money" — best value models under a blended cost cap per 1M tokens. | $0.04 | budget: number（每百万 token 混合成本上限, 美元） |
| smart_top20 Ask "which LLM gives the best value for the money" — top 20 models by value_score, cost and context efficiency halves. | $0.05 | — |
2 paid endpoint(s), 3 free endpoint(s). Price range $0.04 – $0.05. Single call returns up to 20 rows per run.
Below is the actual response from the free endpoint value_digest (truncated). The paid endpoint returns every field and the full record set.
{
"model": "~z-ai/glm-flash-latest",
"value_score": 100.0
}
Delivery guarantee: settle after delivery. If the source fails or returns an empty result, nothing is settled and credits are refunded.
| value_digest | Ask "which LLM gives the best value for the money" — free: one-line call plus top 3 models by value_score. | 30 / IP / day |
| smart_top5 | Ask "which LLM gives the best value for the money" — free: the #1 model by value_score (name + score only). | 30 / IP / day |
| value_methodology | Ask "which LLM gives the best value for the money" — free: how value_score is computed and how to recompute it. | 30 / IP / day |
MCP: https://feegate.org/mcp · REST: https://feegate.org/api/supply/ai-model-value/<tool> · Catalog: https://feegate.org/api/supply/directory
Machine-readable price list: /.well-known/x402.json · Site guide: /llms.txt · Deep dive: AI model value ranking explained · 中文页 / Chinese