Grants

Overview

NIH, NSF and CORDIS awards: who was funded for what, with abstracts and amounts.

status: live
document id: grant_id e.g. nih:R25HG007515
citation: [NIH R25HG007515]
updated: 2026-10

Common calls

Find awardsPOST /v1/grants/search {"query": "单细胞转录组", "filters": {"agency": "nih", "fy": {"gte": 2020}}}

Read one awardGET /v1/grants/read/nih:R25HG007515

Counts per instituteGET /v1/grants/facets?field=ic_or_directorate

The fine print

One NIH document = all yearly awards under a core project number (amount_total is the sum, funding_by_year the breakdown); one NSF document = one award; one CORDIS document = one project (grant_id = cordis:<project id>), org_* is the coordinator and amount_total the EU contribution in EUR (currency=EUR at level=head; NIH / NSF have no currency field and are in USD).
org_country casing is inconsistent in the source (both UNITED STATES and United States, 1.088M awards) — pass both spellings.
`topics` are open labels with tens of thousands of values: good to read, poor to filter on — use research_domain.
Where no abstract exists the summary comes from the title alone (_enrich.basis=title_only).
The index holds no full text: level=full is not available yet (abstracts are already in level=detail; progress reports and publications are not in this corpus).

Search

POST/v1/grants/search

Hybrid retrieval, one card per hit. 2 credits. Free sample: single cell transcriptomics.

Filter fields

field	type · ops	meaning
agency	keyword · eq anynih · nsf · cordis	Funding agency
research_domain	keyword · eq anybiomedical · life_sciences · clinical · public_health · engineering · physical_sciences … 13 values, /facets lists them all	Research domain (model-assigned, closed set of 13)
ic_or_directorate	keyword · eq any	NIH institute, NSF directorate or CORDIS framework programme (FP7 / H2020 / HORIZON …, see facets)
activity_code	keyword · eq any	Funding mechanism: NIH activity code (R01 / R21 / F32 …), NSF award type or CORDIS funding scheme
fy	integer · eq range	Fiscal year, range
start_year	integer · eq range	Project start year, range
end_year	integer · eq range	Project end year, range
amount_total	number · eq range	Total amount, range (USD for NIH / NSF; EU contribution in EUR for CORDIS — pair with agency when filtering across agencies)
org_country	keyword · eq any	Organisation country (source casing is inconsistent — see notes)

7 more, all usable

field	type · ops	meaning
org_state	keyword · eq any	US state
org_name	keyword · eq any	Organisation name (exact)
pi_names	keyword · eq any	PI name as written in the source (NIH uses LAST, FIRST)
topics	keyword · eq any	Research topics (open model-generated labels, very high cardinality)
programs	keyword · eq any	Programme names
core_project_num	keyword · eq any	NIH core project number
is_renewal	bool · eq	Renewal

Parameters

Parameter	Type	Description
query REQUIRED	string	1–1000 characters. Or an array of up to 5 (batch; hits become results[]).
top_k	integer= 10	1–100.
fields	brief · head= brief	head costs one more credit and returns the head view per hit.
filters	json	Filter DSL object (see Getting started); declared fields are listed above.
mode	hybrid · dense · bm25= hybrid	Retrieval mode. Leave it out to use the first.
offset	integer= 0	Pagination.

Example

{ "domain": "grants", "query": "…", "hits": [ { "id": "nih:R25HG007515", "score": 0.83, "brief": { … } } ], "total": null, "coverage": …, "warnings": [],
  "meta": { "request_id": "req_…", "credits": { "charged": 2, "balance": 1998, "pool": "allowance" }, "latency_ms": 41, "cached": false } }

Two layers. 1,328,138 documents carry vectors; the store behind them holds 1,313,241. Hits carry layer: index | pg — pg means the match was by words, not meaning — and coverage says which layer answered (answered_by) and why a fallback did not happen (no_fallback_because). Filters that only one layer has cannot be mixed; the 400 names which belongs where.

Undeclared filter fields return 400 rather than being ignored silently. Filters combine with AND; _or / _not are available.

Read

GET/v1/grants/read/{grant_id}

Three depths. detail is the default. Free sample: nih:R25HG007515.

Levels

level	credits	returns
brief	1	Card: the fields needed to triage, same as in search hits
detail (default)	2	Every structured field (rule-derived plus model-generated; model fields are listed in _enrich.fields)
full	5	Full text (not available yet: abstracts are already in level=detail; progress reports and publications are not in this corpus)

Parameters

Parameter	Type	Description
grant_id (path) REQUIRED	string	Document id (grant_id).
level	brief · detail · full= detail	How deep to read.
format	json · md · html= json	Response shape.

Example

{ "domain": "grants", "id": "nih:R25HG007515", "level": "detail", "view": "head", "data": { … } | "text": "…", "token_count": 1834, "meta": { … } }

The older GET /v1/grants/doc/{id}?view=… still works.

Read many

POST/v1/grants/read

Up to 50 ids, one level. Missing ids come back with error: "not_found" and are not charged.

Parameters

Parameter	Type	Description
ids REQUIRED	string[]	Document ids.
level	brief · detail · full= detail	Level for every id.

Example

{ "domain": "grants", "level": "detail", "docs": [ { "id": "…", "data": { … } }, { "id": "…", "error": "not_found" } ], "meta": { … } }

Facets

GET/v1/grants/facets?field={field}

Legal values for a filter field, so an agent never guesses; precomputed fields carry counts, declared enums come without. Free, no key.

Parameters

Parameter	Type	Description
field REQUIRED	agency · research_domain · ic_or_directorate · activity_code · org_country · org_state	Filter field with facets.
limit	integer= 50	Max values.

Example

{ "domain": "grants", "field": "…", "values": [ { "value": "…", "count": 3120 } ], "meta": { … } }

Askregistered key+ /stream

POST/v1/grants/ask

Agentic Q&A over this domain: the model turns the question into filters plus keywords from the domain's own self-description, reads the hits and answers with [grants: ] citations; /stream is NDJSON with real token deltas. <code>effort</code> low / medium / high = 50 / 100 / 200 credits. Append <code>/stream</code> for NDJSON; the first event is always <code>billing</code>. A failure before the first <code>answer_delta</code> is refunded.</div> <h4>Parameters</h4> <div class="tblwrap"><table class="tbl t3 tparam"> <thead><tr><th>Parameter</th><th>Type</th><th>Description</th></tr></thead> <tbody> <tr> <td>query<span class="req"> REQUIRED</span></td> <td class="ty">string</td> <td>1–2000 characters. Be specific; ask for numbers if you want numbers.</td> </tr><tr> <td>effort</td> <td class="ty">low · medium · high<span class="def">= low</span></td> <td>Reading rounds, and the price: 50 / 100 / 200 credits. Your plan caps it.</td> </tr><tr> <td>verbose</td> <td class="ty">bool<span class="def">= false</span></td> <td>Include the tool-call trace (tool_call / tool_result / thinking events when streaming).</td> </tr><tr> <td>top_k</td> <td class="ty">integer<span class="def">= 10</span></td> <td>Speculative prefetch size.</td> </tr><tr> <td>stream_answer</td> <td class="ty">bool<span class="def">= true</span></td> <td>Streaming only: false emits one answer event instead of deltas.</td> </tr><tr> <td>max_rounds</td> <td class="ty">integer</td> <td>0–8, overrides the effort preset.</td> </tr><tr> <td>force_answer_after</td> <td class="ty">number</td> <td>Seconds; hard cutover into the answer phase.</td> </tr><tr> <td>max_answer_tokens</td> <td class="ty">integer<span class="def">= 4096</span></td> <td>Hitting it sets answer_truncated.</td> </tr><tr> <td>language</td> <td class="ty">string</td> <td>Answer language; defaults to the query’s.</td> </tr> </tbody> </table></div> <h4>Example</h4> <pre class="code">{ "answer": "… [NIH R25HG007515] …", "sources": [ … ], "stats": { "rounds": 1, "elapsed_s": 6.2, "answer_truncated": false }, "coverage"?: { … }, "meta": { "credits": { "charged": 50, … } } }</pre> <div class="callout "><b>Citations are real</b> — every id in <code>answer</code> exists in this domain (format <code>[NIH R25HG007515]</code>). <b><code>sources</code> is the retrieval set</b>, not the citation list. <b><code>answer_truncated</code> means incomplete.</b></div> </section> </div> </div> <aside class="pg" data-playground> <div class="pg-handle" data-pg-handle></div> <div class="pg-head"><b>Playground</b><span class="hint">Follows the section you are reading</span><button class="icon-btn" data-pg-close type="button" aria-label="Close">✕</button></div> <div class="pg-body" data-pg-body></div> <script type="application/json" data-pg-specs>[{"id":"grants-search","domain":"grants","method":"POST","path":"/v1/grants/search","auth":"optional","status":"live","title":{"en":"Search","zh":"检索"},"summary":{"en":"Hybrid retrieval, one card per hit. 2 credits. Free sample: <code>single cell transcriptomics</code>.<h4 class=\"sub\">Filter fields</h4><div class=\"tblwrap\"><table class=\"tbl t3\"><thead><tr><th>field</th><th>type · ops</th><th>meaning</th></tr></thead><tbody><tr><td class=\"mono\">agency</td><td class=\"mono dim\">keyword · eq any<span class=\"vals\">nih · nsf · cordis</span></td><td>Funding agency</td></tr><tr><td class=\"mono\">research_domain</td><td class=\"mono dim\">keyword · eq any<span class=\"vals\">biomedical · life_sciences · clinical · public_health · engineering · physical_sciences <span class=\"dim\">… 13 values, /facets lists them all</span></span></td><td>Research domain (model-assigned, closed set of 13)</td></tr><tr><td class=\"mono\">ic_or_directorate</td><td class=\"mono dim\">keyword · eq any</td><td>NIH institute, NSF directorate or CORDIS framework programme (FP7 / H2020 / HORIZON …, see facets)</td></tr><tr><td class=\"mono\">activity_code</td><td class=\"mono dim\">keyword · eq any</td><td>Funding mechanism: NIH activity code (R01 / R21 / F32 …), NSF award type or CORDIS funding scheme</td></tr><tr><td class=\"mono\">fy</td><td class=\"mono dim\">integer · eq range</td><td>Fiscal year, range</td></tr><tr><td class=\"mono\">start_year</td><td class=\"mono dim\">integer · eq range</td><td>Project start year, range</td></tr><tr><td class=\"mono\">end_year</td><td class=\"mono dim\">integer · eq range</td><td>Project end year, range</td></tr><tr><td class=\"mono\">amount_total</td><td class=\"mono dim\">number · eq range</td><td>Total amount, range (USD for NIH / NSF; EU contribution in EUR for CORDIS — pair with agency when filtering across agencies)</td></tr><tr><td class=\"mono\">org_country</td><td class=\"mono dim\">keyword · eq any</td><td>Organisation country (source casing is inconsistent — see notes)</td></tr></tbody></table></div><details class=\"adv\"><summary>7 more, all usable</summary><div class=\"tblwrap\"><table class=\"tbl t3\"><thead><tr><th>field</th><th>type · ops</th><th>meaning</th></tr></thead><tbody><tr><td class=\"mono\">org_state</td><td class=\"mono dim\">keyword · eq any</td><td>US state</td></tr><tr><td class=\"mono\">org_name</td><td class=\"mono dim\">keyword · eq any</td><td>Organisation name (exact)</td></tr><tr><td class=\"mono\">pi_names</td><td class=\"mono dim\">keyword · eq any</td><td>PI name as written in the source (NIH uses LAST, FIRST)</td></tr><tr><td class=\"mono\">topics</td><td class=\"mono dim\">keyword · eq any</td><td>Research topics (open model-generated labels, very high cardinality)</td></tr><tr><td class=\"mono\">programs</td><td class=\"mono dim\">keyword · eq any</td><td>Programme names</td></tr><tr><td class=\"mono\">core_project_num</td><td class=\"mono dim\">keyword · eq any</td><td>NIH core project number</td></tr><tr><td class=\"mono\">is_renewal</td><td class=\"mono dim\">bool · eq</td><td>Renewal</td></tr></tbody></table></div></details>","zh":"混合检索，每条命中一张卡片。2 credits。免费样例：<code>single cell transcriptomics</code>。<h4 class=\"sub\">过滤字段</h4><div class=\"tblwrap\"><table class=\"tbl t3\"><thead><tr><th>字段</th><th>类型 · op</th><th>含义</th></tr></thead><tbody><tr><td class=\"mono\">agency</td><td class=\"mono dim\">keyword · eq any<span class=\"vals\">nih · nsf · cordis</span></td><td>资助机构</td></tr><tr><td class=\"mono\">research_domain</td><td class=\"mono dim\">keyword · eq any<span class=\"vals\">biomedical · life_sciences · clinical · public_health · engineering · physical_sciences <span class=\"dim\">…共 13 个，/facets 可列全</span></span></td><td>研究领域（模型归类，闭集 13 类）</td></tr><tr><td class=\"mono\">ic_or_directorate</td><td class=\"mono dim\">keyword · eq any</td><td>NIH 研究所 / NSF 学部 / CORDIS 框架计划（FP7 / H2020 / HORIZON …，见 facets）</td></tr><tr><td class=\"mono\">activity_code</td><td class=\"mono dim\">keyword · eq any</td><td>资助机制：NIH 活动代码（R01 / R21 / F32 …）、NSF 奖励类型或 CORDIS fundingScheme</td></tr><tr><td class=\"mono\">fy</td><td class=\"mono dim\">integer · eq range</td><td>财年区间</td></tr><tr><td class=\"mono\">start_year</td><td class=\"mono dim\">integer · eq range</td><td>项目开始年份区间</td></tr><tr><td class=\"mono\">end_year</td><td class=\"mono dim\">integer · eq range</td><td>项目结束年份区间</td></tr><tr><td class=\"mono\">amount_total</td><td class=\"mono dim\">number · eq range</td><td>总金额区间（NIH / NSF 为美元，CORDIS 为欧盟出资、欧元；跨机构按金额筛请同时带 agency）</td></tr><tr><td class=\"mono\">org_country</td><td class=\"mono dim\">keyword · eq any</td><td>承担机构所在国（源数据大小写不统一，见 notes）</td></tr></tbody></table></div><details class=\"adv\"><summary>还有 7 个，照样能用</summary><div class=\"tblwrap\"><table class=\"tbl t3\"><thead><tr><th>字段</th><th>类型 · op</th><th>含义</th></tr></thead><tbody><tr><td class=\"mono\">org_state</td><td class=\"mono dim\">keyword · eq any</td><td>美国州</td></tr><tr><td class=\"mono\">org_name</td><td class=\"mono dim\">keyword · eq any</td><td>承担机构名（精确）</td></tr><tr><td class=\"mono\">pi_names</td><td class=\"mono dim\">keyword · eq any</td><td>PI 姓名（源数据写法，NIH 是姓, 名）</td></tr><tr><td class=\"mono\">topics</td><td class=\"mono dim\">keyword · eq any</td><td>研究主题（模型生成的开放标签，基数很大）</td></tr><tr><td class=\"mono\">programs</td><td class=\"mono dim\">keyword · eq any</td><td>项目/计划名</td></tr><tr><td class=\"mono\">core_project_num</td><td class=\"mono dim\">keyword · eq any</td><td>NIH 核心项目号</td></tr><tr><td class=\"mono\">is_renewal</td><td class=\"mono dim\">bool · eq</td><td>是否续期</td></tr></tbody></table></div></details>"},"params":[{"name":"query","type":"string","required":true,"in":"body","example":"single cell transcriptomics","desc":{"en":"1–1000 characters. Or an array of up to 5 (batch; hits become results[]).","zh":"1–1000 字符。也可以是最多 5 条的数组（批量，hits 变 results[]）。"}},{"name":"top_k","type":"integer","default":"10","in":"body","desc":{"en":"1–100.","zh":"1–100。"}},{"name":"fields","type":"enum","options":["brief","head"],"default":"brief","in":"body","desc":{"en":"head costs one more credit and returns the head view per hit.","zh":"head 多扣 1 credit，每条附 head 视图。"}},{"name":"filters","type":"json","in":"body","example":"","desc":{"en":"Filter DSL object (see Getting started); declared fields are listed above.","zh":"过滤 DSL 对象（见快速开始）；可用字段见上表。"}},{"name":"mode","type":"enum","options":["hybrid","dense","bm25"],"default":"hybrid","in":"body","advanced":false,"desc":{"en":"Retrieval mode. Leave it out to use the first.","zh":"检索模式。不传就用第一个。"}},{"name":"offset","type":"integer","default":"0","in":"body","advanced":true,"desc":{"en":"Pagination.","zh":"翻页。"}}],"example":"{ \"domain\": \"grants\", \"query\": \"…\", \"hits\": [ { \"id\": \"nih:R25HG007515\", \"score\": 0.83, \"brief\": { … } } ], \"total\": null, \"coverage\": …, \"warnings\": [],\n \"meta\": { \"request_id\": \"req_…\", \"credits\": { \"charged\": 2, \"balance\": 1998, \"pool\": \"allowance\" }, \"latency_ms\": 41, \"cached\": false } }","notes":[{"html":{"en":"<b>Two layers.</b> 1,328,138 documents carry vectors; the store behind them holds 1,313,241. Hits carry <code>layer: index | pg</code> — <code>pg</code> means the match was by words, not meaning — and <code>coverage</code> says which layer answered (<code>answered_by</code>) and why a fallback did not happen (<code>no_fallback_because</code>). Filters that only one layer has cannot be mixed; the 400 names which belongs where.","zh":"<b>两层。</b>1,328,138 篇有向量，背后的全量库有 1,313,241 篇。命中带 <code>layer: index | pg</code>——<code>pg</code> 表示按词面匹配而非语义——<code>coverage</code> 说明这次由哪层作答（<code>answered_by</code>）以及为什么没有回落（<code>no_fallback_because</code>）。只属于某一层的过滤字段不能混用，400 会告诉你哪个字段属于哪层。"}},{"html":{"en":"<b>Undeclared filter fields return 400</b> rather than being ignored silently. Filters combine with AND; <code>_or</code> / <code>_not</code> are available.","zh":"<b>用了未声明的过滤字段返回 400</b>，不会静默忽略。过滤条件是 AND；可用 <code>_or</code> / <code>_not</code>。"}}]},{"id":"grants-read","domain":"grants","method":"GET","path":"/v1/grants/read/{grant_id}","auth":"optional","status":"live","title":{"en":"Read","zh":"读"},"summary":{"en":"Three depths. <code>detail</code> is the default. Free sample: <code>nih:R25HG007515</code>.<h4 class=\"sub\">Levels</h4><div class=\"tblwrap\"><table class=\"tbl t3 tnum\"><thead><tr><th>level</th><th>credits</th><th>returns</th></tr></thead><tbody><tr><td class=\"mono\">brief</td><td class=\"mono num\">1</td><td>Card: the fields needed to triage, same as in search hits</td></tr><tr><td class=\"mono\">detail <span class=\"dim\">(default)</span></td><td class=\"mono num\">2</td><td>Every structured field (rule-derived plus model-generated; model fields are listed in _enrich.fields)</td></tr><tr><td class=\"mono\">full</td><td class=\"mono num\">5</td><td>Full text (not available yet: abstracts are already in level=detail; progress reports and publications are not in this corpus)</td></tr></tbody></table></div>","zh":"三档深浅，不传就是 <code>detail</code>。免费样例：<code>nih:R25HG007515</code>。<h4 class=\"sub\">三档</h4><div class=\"tblwrap\"><table class=\"tbl t3 tnum\"><thead><tr><th>深浅</th><th>credits</th><th>返回</th></tr></thead><tbody><tr><td class=\"mono\">brief</td><td class=\"mono num\">1</td><td>卡片：做取舍够用的字段（检索结果里那张）</td></tr><tr><td class=\"mono\">detail <span class=\"dim\">（默认）</span></td><td class=\"mono num\">2</td><td>全部结构化字段（规则字段 + 模型字段，模型字段在 _enrich.fields 里列名）</td></tr><tr><td class=\"mono\">full</td><td class=\"mono num\">5</td><td>全文（建设中：摘要已在 level=detail；项目报告与出版物不在本库）</td></tr></tbody></table></div>"},"params":[{"name":"grant_id","type":"string","required":true,"in":"path","example":"nih:R25HG007515","desc":{"en":"Document id (grant_id).","zh":"文档 id（grant_id）。"}},{"name":"level","type":"enum","options":["brief","detail","full"],"default":"detail","desc":{"en":"How deep to read.","zh":"读多深。"}},{"name":"format","type":"enum","options":["json","md","html"],"default":"json","desc":{"en":"Response shape.","zh":"响应形态。"}}],"example":"{ \"domain\": \"grants\", \"id\": \"nih:R25HG007515\", \"level\": \"detail\", \"view\": \"head\", \"data\": { … } | \"text\": \"…\", \"token_count\": 1834, \"meta\": { … } }","notes":[{"html":{"en":"The older <code>GET /v1/grants/doc/{id}?view=…</code> still works.","zh":"旧写法 <code>GET /v1/grants/doc/{id}?view=…</code> 仍然可用。"}}]},{"id":"grants-read-batch","domain":"grants","method":"POST","path":"/v1/grants/read","auth":"token","status":"live","title":{"en":"Read many","zh":"批量读"},"summary":{"en":"Up to 50 ids, one level. Missing ids come back with <code>error: \"not_found\"</code> and are not charged.","zh":"最多 50 个 id，同一档。查不到的 id 返回 <code>error: \"not_found\"</code>，不扣费。"},"params":[{"name":"ids","type":"array","list":true,"required":true,"in":"body","example":"nih:R25HG007515","desc":{"en":"Document ids.","zh":"文档 id 列表。"}},{"name":"level","type":"enum","options":["brief","detail","full"],"default":"detail","in":"body","desc":{"en":"Level for every id.","zh":"所有 id 共用的档。"}}],"example":"{ \"domain\": \"grants\", \"level\": \"detail\", \"docs\": [ { \"id\": \"…\", \"data\": { … } }, { \"id\": \"…\", \"error\": \"not_found\" } ], \"meta\": { … } }"},{"id":"grants-facets","domain":"grants","method":"GET","path":"/v1/grants/facets","auth":"none","status":"live","title":{"en":"Facets","zh":"Facets"},"summary":{"en":"Legal values for a filter field, so an agent never guesses; precomputed fields carry counts, declared enums come without. Free, no key.","zh":"某个过滤字段的合法值，agent 不用猜；预聚合字段带计数，声明的枚举没有。免费、不需要 key。"},"params":[{"name":"field","type":"enum","options":["agency","research_domain","ic_or_directorate","activity_code","org_country","org_state"],"required":true,"example":"agency","desc":{"en":"Filter field with facets.","zh":"有 facets 的过滤字段。"}},{"name":"limit","type":"integer","default":"50","advanced":true,"desc":{"en":"Max values.","zh":"最多返回多少个值。"}}],"example":"{ \"domain\": \"grants\", \"field\": \"…\", \"values\": [ { \"value\": \"…\", \"count\": 3120 } ], \"meta\": { … } }"},{"id":"grants-ask","domain":"grants","method":"POST","path":"/v1/grants/ask","auth":"registered","status":"live","stream":true,"agentic":true,"title":{"en":"Ask","zh":"问"},"summary":{"en":"Agentic Q&A over this domain: the model turns the question into filters plus keywords from the domain's own self-description, reads the hits and answers with [grants:<grant_id> <title>] citations; /stream is NDJSON with real token deltas. <code>effort</code> low / medium / high = 50 / 100 / 200 credits. Append <code>/stream</code> for NDJSON; the first event is always <code>billing</code>. A failure before the first <code>answer_delta</code> is refunded.","zh":"本域的 agentic 问答：模型按自描述把问题翻成检索（筛选 + 关键词），读详情后作答，引用写成 [grants:<grant_id> <标题>]；/stream 为 NDJSON，answer_delta 是边生成边发的真实片段。<code>effort</code> low / medium / high 对应 50 / 100 / 200 credits。加 <code>/stream</code> 走 NDJSON，第一个事件一定是 <code>billing</code>。首个 <code>answer_delta</code> 之前失败会退款。"},"params":[{"name":"query","type":"string","required":true,"in":"body","example":"single cell transcriptomics","desc":{"en":"1–2000 characters. Be specific; ask for numbers if you want numbers.","zh":"1–2000 字符。问得具体；要数字就直接问数字。"}},{"name":"effort","type":"enum","options":["low","medium","high"],"default":"low","in":"body","desc":{"en":"Reading rounds, and the price: 50 / 100 / 200 credits. Your plan caps it.","zh":"检索轮数，也决定价格：50 / 100 / 200 credits。套餐限制最高档。"}},{"name":"verbose","type":"bool","default":"false","in":"body","desc":{"en":"Include the tool-call trace (tool_call / tool_result / thinking events when streaming).","zh":"返回工具调用轨迹（流式时多 tool_call / tool_result / thinking 事件）。"}},{"name":"top_k","type":"integer","default":"10","in":"body","advanced":true,"desc":{"en":"Speculative prefetch size.","zh":"预取候选数。"}},{"name":"stream_answer","type":"bool","default":"true","in":"body","advanced":true,"desc":{"en":"Streaming only: false emits one answer event instead of deltas.","zh":"仅流式：false 时只发一个 answer 事件。"}},{"name":"max_rounds","type":"integer","in":"body","advanced":true,"desc":{"en":"0–8, overrides the effort preset.","zh":"0–8，覆盖 effort 预设。"}},{"name":"force_answer_after","type":"number","in":"body","advanced":true,"desc":{"en":"Seconds; hard cutover into the answer phase.","zh":"秒；强制切入作答阶段。"}},{"name":"max_answer_tokens","type":"integer","default":"4096","in":"body","advanced":true,"desc":{"en":"Hitting it sets answer_truncated.","zh":"触顶时置 answer_truncated。"}},{"name":"language","type":"string","in":"body","advanced":true,"desc":{"en":"Answer language; defaults to the query’s.","zh":"回答语言，默认跟随 query。"}}],"example":"{ \"answer\": \"… [NIH R25HG007515] …\", \"sources\": [ … ], \"stats\": { \"rounds\": 1, \"elapsed_s\": 6.2, \"answer_truncated\": false }, \"coverage\"?: { … }, \"meta\": { \"credits\": { \"charged\": 50, … } } }","notes":[{"html":{"en":"<b>Citations are real</b> — every id in <code>answer</code> exists in this domain (format <code>[NIH R25HG007515]</code>). <b><code>sources</code> is the retrieval set</b>, not the citation list. <b><code>answer_truncated</code> means incomplete.</b>","zh":"<b>引用是真的</b>——<code>answer</code> 里的每个 id 都存在于本垂域（格式 <code>[NIH R25HG007515]</code>）。<b><code>sources</code> 是召回集</b>，不是引用列表。<b><code>answer_truncated</code> 表示不完整。</b>"}}]}]</script> <script type="application/json" data-pg-strings>{"title":"Playground","hint":"Follows the section you are reading","token":"API token","tokenHint":"fa_live_… key · optional for free samples · stored in this browser only","tokenReq":"API key required (fa_live_…)","send":"Send request","stream":"Stream","response":"Response","events":"Events","answer":"Answer","sources":"Sources","cited":"cited","retrieved":"retrieved","stats":"Stats","coming":"This domain is still building. The request shape is final; sending is disabled until it is live.","open":"Playground","close":"Close","tokens":"tokens","chars":"characters","truncated":"answer truncated","code":"Code","openTab":"Open in a new tab","report":"This one is wrong — report it","quotaHit":"Daily quota used up ({used} / {limit}, resets {reset}). It is a quota, not a rate limit, so retrying will not help: write to {mail} about {grant}.","rateHit":"Over your rpm. Retry in {n} s.","lang":"en","apiBase":"https://api.1stauthor.com","codeBase":"https://api.1stauthor.com","keys":"/dashboard/keys/","fb":"/feedback/","contact":"tommy@chien.io"}</script> </aside> <button class="btn btn-primary pg-fab" data-pg-open type="button">Playground</button> <script type="module" src="/_astro/DocsShell.astro_astro_type_script_index_0_lang.cOZozF12.js"></script> </main> <script type="module" src="/_astro/Base.astro_astro_type_script_index_0_lang.B9qjIrvh.js"></script> </body> </html>