AI Model Marketplace
Catalog Size Is Not Verified CoverageAI 模型市场：目录大不等于覆盖经过验证
A useful marketplace makes model, endpoint and provider provenance visible. Evaluate metadata quality, routing, billing, policy, reliability and lifecycle—not the headline number of models.
有用的模型市场应让模型、端点与供应商来源清晰可见。应评估元数据质量、路由、计费、策略、可靠性与生命周期，而不是模型数量标题。
TL;DR
One model can have several hosted endpoints; a provider can host many models; endpoint behavior and terms can differ.
Capabilities, context, modalities, parameters, region, price unit, data policy, endpoint health and deprecation should drive eligibility.
Run representative prompts and failures against the exact endpoint, not a model family name or marketplace demo.
New hosts, version changes, retirement, policy updates and pricing changes can invalidate a previously correct route.
一个模型可以有多个托管端点；供应商可托管多个模型；端点行为与条款也可能不同。
能力、上下文、模态、参数、区域、计价单位、数据策略、端点健康与弃用应驱动资格判断。
针对具体端点运行代表性提示与故障，而不是只测试模型家族名称或市场 Demo。
新托管方、版本变化、退役、策略更新与价格变化都可能让原本正确的路由失效。
Marketplaces combine discovery, supply and operations模型市场组合发现、供给与运营
Aggregators expose models from multiple creators and hosting providers through one API and billing view. Hosted inference platforms operate serverless or dedicated endpoints. Cloud catalogs align models with a cloud's identity, networking, region, and procurement. Open-source hubs emphasize artifacts, weights, licenses, and community metadata.
Aggregator 通过一个 API 与账单视图提供多个模型创建者和托管 Provider；托管推理平台运营 Serverless 或 Dedicated Endpoint；云目录把模型与云身份、网络、区域和采购对齐；开源 Hub 则强调 Artifact、权重、License 与社区元数据。
These categories overlap, but the listing object is not the same. Determine whether an entry is a model family, a specific version, an artifact, a callable endpoint, a provider route, a fine-tune base, or a deployment recipe. The answer changes what “available,” “price,” “region,” “context,” and “support” mean. Only callable endpoints with verified contract and operational evidence belong in a production routing catalog.
这些类别会重叠，但 Listing 对象并不相同。要先判断条目代表模型家族、准确版本、Artifact、可调用端点、Provider Route、Fine-tune Base 还是部署方案。答案会改变“可用”“价格”“区域”“上下文”和“支持”的含义。只有契约与运行证据经过验证的可调用端点，才应进入生产路由目录。
Treat marketplace metadata as discovery evidence, not truth. Verify creator and provider identity, model version or hash, license and acceptable use, data handling, training or logging policy, supported modalities and tools, context and output limits, tokenizer, regions, rate limits, lifecycle, pricing units, support owner, and native request IDs. Community popularity or a large catalog cannot replace endpoint-level tests.
应把 Marketplace 元数据视为发现证据，而不是事实真源。需要验证 Creator 与 Provider 身份、模型版本或 Hash、License 与可接受用途、数据处理、训练或日志策略、支持模态与工具、上下文和输出限制、Tokenizer、区域、Rate Limit、生命周期、计价单位、支持 Owner 与原生 Request ID。社区热度或大目录无法替代端点级测试。
Marketplace archetypes模型市场类型
| Marketplace type市场类型 | Best fit最适合 | Verify before choosing选择前验证 |
|---|---|---|
| Multi-provider aggregator多供应商聚合器 | One API and bill across models and hosting providers, often with routing and fallback.通过一个 API 与账单连接多个模型和托管供应商，通常含路由与回退。 | Verify provider identity, endpoint selection, markup, privacy, supported parameters and fallback behavior.验证供应商身份、端点选择、加价、隐私、参数支持与回退行为。 |
| Hosted inference catalog托管推理目录 | Serverless and dedicated endpoints for open or proprietary models with platform operations.为开放或专有模型提供无服务器与专属端点及平台运营。 | Pin model version, quantization, context, capacity, cold behavior, region, support and lifecycle.固定模型版本、量化、上下文、容量、冷行为、区域、支持与生命周期。 |
| Cloud model catalog云模型目录 | Models integrated with a cloud's identity, networking, regions, governance and procurement.模型与云身份、网络、区域、治理与采购集成。 | Compare regional availability, API differences, service quotas, data terms and portability.比较区域可用性、API 差异、服务配额、数据条款与可移植性。 |
| Open model hub开放模型 Hub | Artifacts, weights, cards, licenses and community ecosystem for discovery and deployment.用于发现和部署的制品、权重、模型 Card、许可与社区生态。 | A model page is not a production endpoint; verify serving stack, license, security and operating owner.模型页面不是生产端点；需验证 Serving 栈、许可、安全与运营负责人。 |
| AI service marketplaceAI 服务市场 | Broader catalog spanning text, image, audio, video, OCR or other AI functions.更广目录，覆盖文本、图像、音频、视频、OCR 或其他 AI 功能。 | Keep category-specific schemas, quality metrics, asynchronous jobs, storage and price units explicit.显式保留类别特定结构定义、质量指标、异步任务、存储与计价单位。 |
A verified listing needs ten fields已验证 Listing 需要十类字段
Creator, model version, artifact, serving provider, endpoint ID, region, runtime and quantization.
Modalities, context, tools, structured output, reasoning, files, streaming, embeddings and provider extensions.
License, data use, retention, training, residency, price unit, markup, credits, quota and support.
Release, update, deprecation, health, latency, throughput, error rate, request IDs, usage and incident history.
创建者、模型版本、制品、Serving 供应商、端点 ID、区域、运行时与量化。
模态、上下文、工具、结构化输出、推理、文件、流式、Embedding 与供应商扩展。
许可、数据使用、保留、训练、驻留、计价单位、加价、Credits、配额与支持。
发布、更新、弃用、健康、延迟、吞吐、错误率、请求 ID、用量与事故历史。
Turn a listing into a verified endpoint把 Listing 转为已验证端点
Use a promotion pipeline rather than letting applications call new listings immediately. A candidate first passes documentary eligibility, then protocol conformance, workload quality, safety, load, failure, privacy, and commercial review. Publish an approved internal alias only after an owner accepts the evidence and defines an expiry or revalidation trigger.
不要让应用直接调用新 Listing，应建立晋级 Pipeline。候选先通过文档资格审查，再通过协议一致性、工作负载质量、安全、负载、故障、隐私与商业审查。只有 Owner 接受证据并定义到期或重新验证触发条件后，才能发布获批内部别名。
- Filter by hard capability, region, data, license, acceptable-use, price-unit, procurement, and contract requirements.
- Resolve exact model and endpoint identity; do not approve a mutable family name without version and lifecycle evidence.
- Run conformance, quality, safety, load, quota, stream-interruption, and provider-failure tests against the exact endpoint route.
- Pin endpoint, model version, adapter, and policy; store native provider IDs, marketplace identifiers, source URLs, and verification time together.
- Reconcile measured usage and tool charges to the marketplace or provider invoice before approving cost claims.
- Monitor health, price, policy, license, provider, and lifecycle events; require review before automatic substitutions.
- 按硬性能力、区域、数据、License、可接受用途、计价单位、采购与合同要求过滤。
- 解析准确模型和端点身份；如果缺少版本与生命周期证据，不应批准可变的家族名称。
- 针对准确端点路由运行一致性、质量、安全、负载、配额、流中断与 Provider 故障测试。
- 固定端点、模型版本、Adapter 与策略，并同时存储原生 Provider ID、Marketplace 标识、来源 URL 与验证时间。
- 在批准成本结论前，将实测用量和工具费用与 Marketplace 或 Provider 账单对齐。
- 监控健康、价格、策略、License、Provider 与生命周期事件；自动替换前必须经过评审。
Build an internal catalog from verified marketplace evidence用已验证市场证据构建内部目录
Ingest marketplace metadata as untrusted candidates. A verification pipeline applies eligibility, contract tests, quality thresholds and operational probes. Only approved endpoint versions enter the internal catalog. Routing references internal aliases, while traces preserve external model, endpoint and provider IDs for provenance and billing.
把市场元数据作为不受信候选导入。验证管线执行资格判断、契约测试、质量阈值与运行探测；只有获批端点版本进入内部目录。路由引用内部别名，调用链则保留外部模型、端点与供应商 ID 供来源和计费。
Production rule: a large marketplace accelerates discovery; production trust begins only after endpoint-level verification.
生产规则：大型市场加速发现；生产信任只在端点级验证后开始。
A model marketplace is not a capability marketplace模型市场不是能力市场
Model marketplaces supply inference endpoints. QVeris indexes broader real-world capabilities: APIs, tools, services and live data. An agent may choose a model from a marketplace, then use QVeris to discover the capability that completes the task.
模型市场提供推理端点；QVeris 索引更广的现实能力：API、工具、服务与实时数据。智能体可以先从市场选择模型，再用 QVeris 发现完成任务的能力。
FAQ
A catalog that helps users discover, access or deploy models and often connects listings to hosted endpoints, providers or billing.
Only after filtering for your required capabilities, regions, policy, endpoint quality, lifecycle and support.
Marketplaces simplify discovery and supply; direct providers preserve native control and may fit committed spend or critical features.
帮助用户发现、访问或部署模型的目录，通常把 Listing 连接到托管端点、供应商或账单。
只有在按所需能力、区域、策略、端点质量、生命周期与支持过滤后才重要。
市场简化发现与供给；直连保留原生控制，并可能更适合承诺支出或关键功能。