Semantic Scholar references API
Use the Semantic Scholar references API to retrieve referenced papers and the citation relationships published by the source. Provide the citing paper’s identifier and optionally filter intent or ordering to inspect the papers it references, their citation contexts and influence flags in the backward citation direction. Trace the sources a paper relies on, inspect its citation context, or build a backward-reading list from a known publication. References follow the selected record’s backward citation relationships; the amount of bibliographic detail depends on the source endpoint. The detail page provides request and response examples, supported parameters, and usage pricing.
- Selected price
- $0.002 / billing creditPublished pricing
- Sellers / implementations
- 1 / 1
- Requests · 30d
- —Loading...
- Success rate · 30d
- —Loading...
| Seller | Pricing | Requests · 30d | Performance | Access |
|---|---|---|---|---|
apishCurrent Semantic Scholar references API · GET · View API reference | $0.002 / billing credit | — | —successP50— |
Run sends a real API request. Charges follow the published API contract.
Response structure
attributionstringcachedbooleancountintegercredits_usedintegeridstringintentstringintent_countsobjectbackgroundintegermethodologyintegerresultinteger
items(object | string)[]abstractstringauthors(object | string)[]author_idstringnamestring
citation_countintegercontexts(object | string)[]intentsstring[]textstring
corpus_idintegerfields_of_studystring[]is_influentialbooleanpaper_idstringreference_countintegertitlestringtldrstringurlstringvenuestringyearinteger
next_pageintegerpageintegerpaper_idstringsortstringtotalintegertotal_pagesinteger
// Inferred from response examples. Fields are optional and other fields may be returned.
export type ApiResponse = {
attribution?: string;
cached?: boolean;
count?: number;
credits_used?: number;
id?: string;
intent?: string;
intent_counts?: {
background?: number;
methodology?: number;
result?: number;
};
items?: Array<{
abstract?: string;
authors?: Array<{
author_id?: string;
name?: string;
} | string>;
citation_count?: number;
contexts?: Array<{
intents?: Array<string>;
text?: string;
} | string>;
corpus_id?: number;
fields_of_study?: Array<string>;
is_influential?: boolean;
paper_id?: string;
reference_count?: number;
title?: string;
tldr?: string;
url?: string;
venue?: string;
year?: number;
} | string>;
next_page?: number;
page?: number;
paper_id?: string;
sort?: string;
total?: number;
total_pages?: number;
};- Method
- GET
- Endpoint
https://api.openany.si/v1/agent-apis/apish/semantic-scholar/v1/references- Content type
- application/json
- Authentication
Authorization: Bearer $OPENANY_API_KEY
curl \
'https://api.openany.si/v1/agent-apis/apish/semantic-scholar/v1/references?id=ARXIV%3A1706.03762&output=json' \
-X GET \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H 'Content-Type: application/json'Input parameters
Fields in this listing; additional options and input encoding can vary by provider.
| Parameter | Location | Type | Required | Description |
|---|---|---|---|---|
id | URL query parametersquery | string | Yes | Paper id: a Semantic Scholar id (40 hex characters), `CorpusId:<n>`, `DOI:<doi>`, `ARXIV:<id>`, `PMID:<n>`, `PMCID:<id>`, `MAG:<n>`, `ACL:<id>`, `URL:<link>`, a bare DOI or arXiv id, or a semanticscholar.org / doi.org / arxiv.org link. |
sort | URL query parametersquery | string | No | Order. enum: "relevance", "influential", "newest" |
intent | URL query parametersquery | string | No | Only references with this intent. enum: "all", "background", "methodology", "result" |
page | URL query parametersquery | integer | No | Page number, from 1. |
raw | URL query parametersquery | string | No | 0 leaves out the bulky `raw` source blocks (often 10-30x smaller). enum: "0", "1" |
fields | URL query parametersquery | string | No | Comma-separated fields to return, e.g. `posts.id,posts.title`. Call metadata is always included. |
fresh | URL query parametersquery | string | No | 1 skips the 24-hour cache and fetches live. enum: "1" |
output | URL query parametersquery | string | No | JSON only for this OpenAny product. Omit output or use json; CSV and NDJSON exports are not exposed. enum: "json" |
records | URL query parametersquery | string | No | Native CSV/NDJSON record selector; it has no effect on this JSON-only product. |
Required markers inside a nested object or variant apply when that object or variant is used.
Sample response
Sample response · Documented HTTP 200 Example from the provider's documentation. Field values in your results will differ.
{
"attribution": "Data: Semantic Scholar (Allen Institute for AI)",
"cached": false,
"count": 10,
"credits_used": 1,
"id": "ARXIV:1706.03762",
"intent": "all",
"intent_counts": {
"background": 19,
"methodology": 13,
"result": 2
},
"items": [
{
"abstract": "Several mechanisms to focus attention of a neural network on selected parts of its input or memory have been used successfully in deep learn…",
"authors": [
{
"author_id": "40527594",
"name": "Lukasz Kaiser"
},
{
"author_id": "1751569",
"name": "Samy Bengio"
}
],
"citation_count": 62,
"contexts": [
{
"intents": [],
"text": "We trained our models on one machine with 8 NVIDIA P100 GPUs."
},
{
"intents": [],
"text": "We estimate the number of floating point operations used to train a model by multiplying the training time, the number of GPUs used, and an …"
},
"… 3 more"
],
"corpus_id": 11250862,
"fields_of_study": [
"Computer Science"
],
"is_influential": true,
"paper_id": "735d547fc75e0772d2a78c46a1cc5fad7da1474c",
"reference_count": 27,
"title": "Can Active Memory Replace Attention?",
"tldr": "An extended model of active memory is proposed that matches existing attention models on neural machine translation and generalizes better t…",
"url": "https://www.semanticscholar.org/paper/Can-Active-Memory-Replace-Attention-Kaiser-Bengio/735d547fc75e0772d2a78c46a1cc5fad7da1474c",
"venue": "NIPS",
"year": 2016
},
{
"abstract": "We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory N…",
"authors": [
{
"author_id": "2265067",
"name": "Sainbayar Sukhbaatar"
},
{
"author_id": "3149531",
"name": "A. Szlam"
},
"… 2 more"
],
"citation_count": 2807,
"contexts": [
{
"intents": [
"background"
],
"text": "End-to-end memory networks are based on a recurrent attention mechanism instead of sequencealigned recurrence and have been shown to perform…"
}
],
"corpus_id": 1399322,
"fields_of_study": [
"Computer Science"
],
"is_influential": false,
"paper_id": "4f10b9f47c5bb6b54dd4f5ca8d9fa2c0bbd7ec5e",
"reference_count": 25,
"title": "End-To-End Memory Networks",
"tldr": "A neural network with a recurrent attention model over a possibly large external memory that is trained end-to-end, and hence requires signi…",
"url": "https://www.semanticscholar.org/paper/End-To-End-Memory-Networks-Sukhbaatar-Szlam/4f10b9f47c5bb6b54dd4f5ca8d9fa2c0bbd7ec5e",
"venue": "NIPS",
"year": 2015
},
"… 8 more"
],
"next_page": 2,
"page": 1,
"paper_id": "204e3073870fae3d05bcbc2f6a8e263d9b72e776",
"sort": "relevance",
"total": 41,
"total_pages": 5
}Composite rule pricing
Calculated from input parameters and actual returned quantities. Estimate the maximum cost before calling.
Base fee: $0.000000. One matching variant replaces the base fee. Matching add-ons and quantity charges are added.
| Fee item | Price | Metering source | When | Quantity limit |
|---|---|---|---|---|
| Actual API.SH credits consumed | $0.002000 / billing credit | Response · /credits_used · Numeric value | Always | 1 billing credit · Decimal places: 0 |
Each quantity charge is rounded before summing: ceil. Requests exceeding this cost limit are rejected; it is not a price cap: $0.002000.
Response quantities settle after the response. Before execution, the maximum quantity determines the reservation; unused reservation is released. Missing or invalid quantities are not treated as zero.
Pricing parameters and defaults
[]
Agent integration
Copy the resource contract without sharing an API key.
View API Markdown
# Semantic Scholar references API
Use the Semantic Scholar references API to retrieve referenced papers and the citation relationships published by the source. Provide the citing paper’s identifier and optionally filter intent or ordering to inspect the papers it references, their citation contexts and influence flags in the backward citation direction. Trace the sources a paper relies on, inspect its citation context, or build a backward-reading list from a known publication. References follow the selected record’s backward citation relationships; the amount of bibliographic detail depends on the source endpoint. The detail page provides request and response examples, supported parameters, and usage pricing.
Documentation: https://openany.si/apis/4dd6c5aa-4a28-4186-ba4c-f84d4b3705c4
Method: GET
Endpoint: https://api.openany.si/v1/agent-apis/apish/semantic-scholar/v1/references
Price: $0.002 / billing credit
Provider: apish
Contract revision: 2
Price source: OpenAny public API contract and documented provider unit rates. Price update time: not supplied.
Use OPENANY_API_KEY from the environment. API Key calls use your shared balance.
## Prepared request
```bash
curl \
'https://api.openany.si/v1/agent-apis/apish/semantic-scholar/v1/references?id=ARXIV%3A1706.03762&output=json' \
-X GET \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H 'Content-Type: application/json'
```
## API contract
```json
{
"resource_type": "api",
"name": "Semantic Scholar references API",
"endpoint": "https://api.openany.si/v1/agent-apis/apish/semantic-scholar/v1/references",
"method": "GET",
"content_type": "none",
"execution_mode": "sync",
"authentication": {
"type": "bearer",
"environment_variable": "OPENANY_API_KEY"
},
"inputs": [
{
"description": "Paper id: a Semantic Scholar id (40 hex characters), `CorpusId:<n>`, `DOI:<doi>`, `ARXIV:<id>`, `PMID:<n>`, `PMCID:<id>`, `MAG:<n>`, `ACL:<id>`, `URL:<link>`, a bare DOI or arXiv id, or a semanticscholar.org / doi.org / arxiv.org link.",
"location": "query",
"name": "id",
"nullable": false,
"required": true,
"type": "string"
},
{
"description": "Order.",
"enum_values": [
"relevance",
"influential",
"newest"
],
"location": "query",
"name": "sort",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Only references with this intent.",
"enum_values": [
"all",
"background",
"methodology",
"result"
],
"location": "query",
"name": "intent",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Page number, from 1.",
"location": "query",
"name": "page",
"nullable": false,
"required": false,
"type": "integer"
},
{
"description": "0 leaves out the bulky `raw` source blocks (often 10-30x smaller).",
"enum_values": [
"0",
"1"
],
"location": "query",
"name": "raw",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Comma-separated fields to return, e.g. `posts.id,posts.title`. Call metadata is always included.",
"location": "query",
"name": "fields",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "1 skips the 24-hour cache and fetches live.",
"enum_values": [
"1"
],
"location": "query",
"name": "fresh",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "JSON only for this OpenAny product. Omit output or use json; CSV and NDJSON exports are not exposed.",
"enum_values": [
"json"
],
"location": "query",
"name": "output",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Native CSV/NDJSON record selector; it has no effect on this JSON-only product.",
"location": "query",
"name": "records",
"nullable": false,
"required": false,
"type": "string"
}
],
"billing": {
"currency": "USD",
"mode": "rules",
"parameters": [],
"policy_version": 2,
"sale": {
"addons": [],
"base_price_micro_usd": "0",
"max_cost_micro_usd": "2000",
"quantities": [
{
"id": "upstream_credits",
"label": "Actual API.SH credits consumed",
"max_quantity": "1",
"measure": "value",
"pointer": "/credits_used",
"price_micro_usd": "2000",
"quantity_scale": 0,
"source": "response",
"unit": "credit",
"unit_quantity": "1"
}
],
"rounding": "ceil",
"variants": []
}
},
"examples": [
{
"http_status": 200,
"name": "Official example · Official documentation response · Supplier-tr",
"request": {
"body": null,
"headers": {},
"path": {},
"query": {
"id": "ARXIV:1706.03762",
"output": "json"
}
},
"response_body": {
"attribution": "Data: Semantic Scholar (Allen Institute for AI)",
"cached": false,
"count": 10,
"credits_used": 1,
"id": "ARXIV:1706.03762",
"intent": "all",
"intent_counts": {
"background": 19,
"methodology": 13,
"result": 2
},
"items": [
{
"abstract": "Several mechanisms to focus attention of a neural network on selected parts of its input or memory have been used successfully in deep learn…",
"authors": [
{
"author_id": "40527594",
"name": "Lukasz Kaiser"
},
{
"author_id": "1751569",
"name": "Samy Bengio"
}
],
"citation_count": 62,
"contexts": [
{
"intents": [],
"text": "We trained our models on one machine with 8 NVIDIA P100 GPUs."
},
{
"intents": [],
"text": "We estimate the number of floating point operations used to train a model by multiplying the training time, the number of GPUs used, and an …"
},
"… 3 more"
],
"corpus_id": 11250862,
"fields_of_study": [
"Computer Science"
],
"is_influential": true,
"paper_id": "735d547fc75e0772d2a78c46a1cc5fad7da1474c",
"reference_count": 27,
"title": "Can Active Memory Replace Attention?",
"tldr": "An extended model of active memory is proposed that matches existing attention models on neural machine translation and generalizes better t…",
"url": "https://www.semanticscholar.org/paper/Can-Active-Memory-Replace-Attention-Kaiser-Bengio/735d547fc75e0772d2a78c46a1cc5fad7da1474c",
"venue": "NIPS",
"year": 2016
},
{
"abstract": "We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory N…",
"authors": [
{
"author_id": "2265067",
"name": "Sainbayar Sukhbaatar"
},
{
"author_id": "3149531",
"name": "A. Szlam"
},
"… 2 more"
],
"citation_count": 2807,
"contexts": [
{
"intents": [
"background"
],
"text": "End-to-end memory networks are based on a recurrent attention mechanism instead of sequencealigned recurrence and have been shown to perform…"
}
],
"corpus_id": 1399322,
"fields_of_study": [
"Computer Science"
],
"is_influential": false,
"paper_id": "4f10b9f47c5bb6b54dd4f5ca8d9fa2c0bbd7ec5e",
"reference_count": 25,
"title": "End-To-End Memory Networks",
"tldr": "A neural network with a recurrent attention model over a possibly large external memory that is trained end-to-end, and hence requires signi…",
"url": "https://www.semanticscholar.org/paper/End-To-End-Memory-Networks-Sukhbaatar-Szlam/4f10b9f47c5bb6b54dd4f5ca8d9fa2c0bbd7ec5e",
"venue": "NIPS",
"year": 2015
},
"… 8 more"
],
"next_page": 2,
"page": 1,
"paper_id": "204e3073870fae3d05bcbc2f6a8e263d9b72e776",
"sort": "relevance",
"total": 41,
"total_pages": 5
}
}
]
}
```Error handling
| Status | Next step |
|---|---|
400 | Check the offering and request fields. |
401 / 403 | Verify your credentials and access permissions. |
402 | Inspect the selected access mode and returned payment requirements. |
429 | Respect the returned rate limit and retry guidance. |
5xx | Inspect the error and usage record before retrying a paid operation. |
Official example · Official documentation response · Supplier-tr
Example from the provider's documentation. Field values in your results will differ.
Prepare your environment
Use a terminal with cURL installed.
Use an OpenAny API key with shared-balance access. Confirm availability and price before running; a call may charge your balance.
Set the key in your terminal using the hidden prompt below. Keep its value out of source files and logs.
Terminal · macOS / Linuxprintf 'OpenAny API key: ' read -r -s OPENANY_API_KEY export OPENANY_API_KEY printf '\n'Run the request
Paste the complete command below into your terminal.
Values to replace before running 9
Review these request fields before running. Keep the published provider and request method unchanged.
id- Paper id: a Semantic Scholar id (40 hex characters), `CorpusId:<n>`, `DOI:<doi>`, `ARXIV:<id>`, `PMID:<n>`, `PMCID:<id>`, `MAG:<n>`, `ACL:<id>`, `URL:<link>`, a bare DOI or arXiv id, or a semanticscholar.org / doi.org / arxiv.org link.
sort- Order.
intent- Only references with this intent.
page- Page number, from 1.
raw- 0 leaves out the bulky `raw` source blocks (often 10-30x smaller).
fields- Comma-separated fields to return, e.g. `posts.id,posts.title`. Call metadata is always included.
fresh- 1 skips the 24-hour cache and fetches live.
output- JSON only for this OpenAny product. Omit output or use json; CSV and NDJSON exports are not exposed.
records- Native CSV/NDJSON record selector; it has no effect on this JSON-only product.
Terminal · cURLcurl \ 'https://api.openany.si/v1/agent-apis/apish/semantic-scholar/v1/references?id=ARXIV%3A1706.03762&output=json' \ -X GET \ -H "Authorization: Bearer $OPENANY_API_KEY" \ -H 'Content-Type: application/json'Check the response
Sample response · Documented HTTP 200
Sample response{ "attribution": "Data: Semantic Scholar (Allen Institute for AI)", "cached": false, "count": 10, "credits_used": 1, "id": "ARXIV:1706.03762", "intent": "all", "intent_counts": { "background": 19, "methodology": 13, "result": 2 }, "items": [ { "abstract": "Several mechanisms to focus attention of a neural network on selected parts of its input or memory have been used successfully in deep learn…", "authors": [ { "author_id": "40527594", "name": "Lukasz Kaiser" }, { "author_id": "1751569", "name": "Samy Bengio" } ], "citation_count": 62, "contexts": [ { "intents": [], "text": "We trained our models on one machine with 8 NVIDIA P100 GPUs." }, { "intents": [], "text": "We estimate the number of floating point operations used to train a model by multiplying the training time, the number of GPUs used, and an …" }, "… 3 more" ], "corpus_id": 11250862, "fields_of_study": [ "Computer Science" ], "is_influential": true, "paper_id": "735d547fc75e0772d2a78c46a1cc5fad7da1474c", "reference_count": 27, "title": "Can Active Memory Replace Attention?", "tldr": "An extended model of active memory is proposed that matches existing attention models on neural machine translation and generalizes better t…", "url": "https://www.semanticscholar.org/paper/Can-Active-Memory-Replace-Attention-Kaiser-Bengio/735d547fc75e0772d2a78c46a1cc5fad7da1474c", "venue": "NIPS", "year": 2016 }, { "abstract": "We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory N…", "authors": [ { "author_id": "2265067", "name": "Sainbayar Sukhbaatar" }, { "author_id": "3149531", "name": "A. Szlam" }, "… 2 more" ], "citation_count": 2807, "contexts": [ { "intents": [ "background" ], "text": "End-to-end memory networks are based on a recurrent attention mechanism instead of sequencealigned recurrence and have been shown to perform…" } ], "corpus_id": 1399322, "fields_of_study": [ "Computer Science" ], "is_influential": false, "paper_id": "4f10b9f47c5bb6b54dd4f5ca8d9fa2c0bbd7ec5e", "reference_count": 25, "title": "End-To-End Memory Networks", "tldr": "A neural network with a recurrent attention model over a possibly large external memory that is trained end-to-end, and hence requires signi…", "url": "https://www.semanticscholar.org/paper/End-To-End-Memory-Networks-Sukhbaatar-Szlam/4f10b9f47c5bb6b54dd4f5ca8d9fa2c0bbd7ec5e", "venue": "NIPS", "year": 2015 }, "… 8 more" ], "next_page": 2, "page": 1, "paper_id": "204e3073870fae3d05bcbc2f6a8e263d9b72e776", "sort": "relevance", "total": 41, "total_pages": 5 }
Loading related APIs…
Common questions
Do I need a separate key for every provider?
Use your OpenAny API key for standard API access. Read it from OPENANY_API_KEY in your environment and keep it out of prompts, source code and logs.
Are these providers interchangeable?
No. Each offering has its own inputs, pricing and response contract. Selecting a catalog offering does not establish automatic routing or fallback. Confirm the service contract before calling.
How is this API billed?
API-key calls use your shared balance at the selected implementation's published rate. Check the billing unit and request-specific pricing rules before making a paid call. Recorded usage determines the final charge under that contract.
Where do the price and contract come from?
The selected implementation publishes its provider, request contract, revision and billing rules through OpenAny's public API catalog. A revision number identifies a contract version, not a price update date. A price update timestamp is not supplied; do not treat a page date as one.
How do OpenAny Balance and x402 differ?
OpenAny Balance uses an API key and one shared balance. Card, USDC and x402 top-ups, card auto top-up and USDC subscriptions fund that balance; available routes appear on the Credits page. Direct x402 is a separate pay-per-request flow, available only on listings that show it and requiring an authorized payment client.
Does Playground send a paid request?
Yes. After you sign in, Run sends a real API request using an active OpenAny API key. Charges follow the published API contract and use your shared balance. Selecting an implementation, editing inputs and viewing sample responses do not send requests.
Use Semantic Scholar references API with your agent
Inspect endpoint contracts and confirm availability and pricing before a paid call.