{ "aboutHtml": "

openai/gpt-4.1-mini:batch er batchoppføringen for uavhengige tekstoppgaver. En konkret bruk er uttrekk av samme feltsett fra mange tilførte kundesamtaler, med ett resultat per samtale. Velg når senere innhenting passer fremfor direkte assistentsvar.

Send inline requests-liste til /v1/batches med endpoint=/v1/chat/completions og unik custom_id for hvert element. Hver body inneholder messages; completion_window godtar 24h. Metoden avregnes fra saldoen og avviser opprettelse av batchjobber med abonnementsfakturering. Godkjent batchinndata er tekst. Files/input_file_id-opplastingsflyt tilbys ikke. Bredere Mini-beskrivelse lover ikke interaktiv responstid for batchruten.

", "aboutText": "openai/gpt-4.1-mini:batch er batchoppføringen for uavhengige tekstoppgaver. En konkret bruk er uttrekk av samme feltsett fra mange tilførte kundesamtaler, med ett resultat per samtale. Velg når senere innhenting passer fremfor direkte assistentsvar. Send inline requests-liste til /v1/batches med endpoint=/v1/chat/completions og unik custom_id for hvert element. Hver body inneholder messages; completion_window godtar 24h. Metoden avregnes fra saldoen og avviser opprettelse av batchjobber med abonnementsfakturering. Godkjent batchinndata er tekst. Files/input_file_id-opplastingsflyt tilbys ikke. Bredere Mini-beskrivelse lover ikke interaktiv responstid for batchruten.", "editorialOverlay": { "copy_fields": { "about_html": "

openai/gpt-4.1-mini:batch er batchoppføringen for uavhengige tekstoppgaver. En konkret bruk er uttrekk av samme feltsett fra mange tilførte kundesamtaler, med ett resultat per samtale. Velg når senere innhenting passer fremfor direkte assistentsvar.

Send inline requests-liste til /v1/batches med endpoint=/v1/chat/completions og unik custom_id for hvert element. Hver body inneholder messages; completion_window godtar 24h. Metoden avregnes fra saldoen og avviser opprettelse av batchjobber med abonnementsfakturering. Godkjent batchinndata er tekst. Files/input_file_id-opplastingsflyt tilbys ikke. Bredere Mini-beskrivelse lover ikke interaktiv responstid for batchruten.

", "short_text": "Batch for uavhengig tekst med custom_id-kobling og valgfritt 24h-fullføringsvindu." }, "copy_sha256": "d21dc06496e8d52c240a4f9b3f42a5d65c60b6c6355fa3ffd3030448e1d9c19e", "copy_source": { "locale": "nb", "pack_sha256": "0f56d90ba41881e1134accf82e57338f246f8753ca4c0cee929aaffada5d10e7", "record_model_id": "openai/gpt-4.1-mini:batch", "source_facts_sha256": "847c5fb5a7edd102ca7647a1f5d514a92ed17816f9bf480813d699dafcb9962c", "validation_sha256": "a2ac2f28056280fc0b2ea34a501bf156d5ce155406e57e708edf30bfdf6bfdc6" }, "html_sha256": "68a441a0a432abdd93706f2920bfc0e3320f701ece4ec610f0f3c4ae952fd6a3", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "nb", "methods": [ { "html": "
O

OpenAI: GPT-4.1 Mini (batch)

OpenAI /openai/gpt-4.1-mini:batch

Start

Batch for uavhengig tekst med custom_id-kobling og valgfritt 24h-fullføringsvindu.

Godkjente inndata
Tekst
Resultater
Tekst
Om modellen

Denne beskrivelsen dekker modellens funksjoner. Tilgjengelige inndata, utdata og alternativer i Ailoot er oppført nedenfor for den valgte metoden.

openai/gpt-4.1-mini:batch er batchoppføringen for uavhengige tekstoppgaver. En konkret bruk er uttrekk av samme feltsett fra mange tilførte kundesamtaler, med ett resultat per samtale. Velg når senere innhenting passer fremfor direkte assistentsvar.

Send inline requests-liste til /v1/batches med endpoint=/v1/chat/completions og unik custom_id for hvert element. Hver body inneholder messages; completion_window godtar 24h. Metoden avregnes fra saldoen og avviser opprettelse av batchjobber med abonnementsfakturering. Godkjent batchinndata er tekst. Files/input_file_id-opplastingsflyt tilbys ikke. Bredere Mini-beskrivelse lover ikke interaktiv responstid for batchruten.

Tilgjengelig i Ailoot · inndata & metoder

Ailoot Ultra · Batchbehandling POST /v1/batches
Inndatatyper
text
Utdatatyper
text
Utdataformat
JSON fra results[].response.body direkte i svaret
FeltTypeKravVerdier & grenserStandard
FeltendpointTypestringKravPåkrevdVerdier & grenser
/v1/chat/completions
Standard—
FeltmodelTypestringKravPåkrevdVerdier & grenser
openai/gpt-4.1-mini:batch
Standard—
FeltrequestsTypebatch_item[]KravPåkrevdVerdier & grenser
Minste antall elementer: 1
Standard—
Feltrequests[].custom_idTypestringKravPåkrevdVerdier & grenserStandard—
Feltrequests[].body.messagesTypemessage[]KravPåkrevdVerdier & grenserStandard—
Feltcompletion_windowTypestringKravValgfrittVerdier & grenser
24h
Standard—
FeltproviderTypeobject|nullKravValgfrittVerdier & grenserStandard—
Feltrequests[].body.modelTypestringKravValgfrittVerdier & grenser
openai/gpt-4.1-mini:batch, openai/gpt-4.1-mini
Standard—
Feltprovider.onlyTypestring[]KravValgfrittVerdier & grenser
openai
Standard—
Feltprovider.allow_fallbacksTypeboolean|nullKravValgfrittVerdier & grenser
false, null
Standard—
Metodeparametere og livssyklus
ParameterAvtale
Parametercontent_typeAvtaleapplication/json
ParameterrequiredAvtaleendpoint, model, requests
Parametermaterial_typesAvtaletext
ParameterrepresentationAvtalerequests[] direkte i forespørselen; hvert element har custom_id og body
Parameterrequest_endpoint_profileAvtale/v1/chat/completions
Parameterfile_materialAvtaleKlienten kan lese det faktiske UTF-8-kodede JSONL-innholdet lokalt inn i requests[]. Feltet purpose for opplasting, input_file_id og filreferanser brukes ikke. Manglende eller tomt kundemateriale stopper klargjøringen før POST.
Parameterserialization_orderAvtaleendpoint, model, provider (hvis angitt), completion_window (hvis angitt), requests til slutt
Parameteroptional_controlsAvtaleprovider.only, provider.allow_fallbacks, completion_window
Parameterschema_scopeAvtaleForespørselsinnhold for tekstbasert Chat Completions lagt direkte inn i det dokumenterte Batch-formatet.

Livssyklus: asynchronous

GET /v1/batches/{operation_id} · faktisk response.id fra den opprinnelige opprettelsen; samme bruker/nøkkel/gruppe

Priser

Tariffopplysninger legger ikke til forespørselsvalg. Støttede parametere står ved den valgte metoden.

Hurtigmodus
Ikke angitt Når hurtigmodus er valgt
Flex-modus
Ikke angitt Når flex-modus er valgt
Maksimal resonneringsinnsats
Ikke angitt Når justeringen «default» brukes for maksimal resonneringsinnsats
Priser for eksplisitt mellomlagring
Ikke aktivert Når eksplisitt mellomlagring forespørres

Ailoot-satser

Priser etter konfigurasjon

Knytt hver kostnad til de viste vilkårene. Bruk én sats for hvert sett med alternative konfigurasjoner.

KonfigurasjonPrisplanKonteksttokener, mer ennKonteksttokener, opptil og medKostnad
KonfigurasjonGrunnpriser for tokenerPrisplanGrunnsatsKonteksttokener, mer enn—Konteksttokener, opptil og medIngen øvre grenseKostnad
Inndata · Inngående tokener $0.0004 / 1K tokener
Utdata · Utgående tokener $0.0016 / 1K tokener
Inndata · Lesing fra hurtigbuffer $0.0001 / 1K tokener
Inndata · Skriving til hurtigbuffer — / 1K tokener
Inndata · Skriving til hurtigbuffer, 1 time — / 1K tokener
KonfigurasjonNivå 1 for forespørselslengdePrisplan—Konteksttokener, mer enn0Konteksttokener, opptil og medIngen øvre grenseKostnad
Inndata · Inngående tokener $0.0004 / 1K tokener
Utdata · Utgående tokener $0.0016 / 1K tokener
Inndata · Lesing fra hurtigbuffer $0.0001 / 1K tokener
Inndata · Skriving til hurtigbuffer — / 1K tokener
Inndata · Skriving til hurtigbuffer, 1 time — / 1K tokener

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. Slik fungerer reservasjon og oppgjør →

Eksempelforespørsler

Ailoot Ultra · Batchbehandling

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{"endpoint":"/v1/chat/completions","model":"openai/gpt-4.1-mini:batch","requests":[{"custom_id":"req-0001","body":{"messages":[{"role":"user","content":"Hello!"}],"max_tokens":16}}]}')\nPath("batch-request.json").write_text(json.dumps(body,ensure_ascii=False),encoding="utf-8")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\n

Motta og lagre resultater

Ailoot Ultra · Batchbehandling

JSON fra results[].response.body direkte i svaret

Kontroller jobbstatus
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nBATCH_OPERATION_ID="$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path("batch-create-response.json").read_text(encoding="utf-8"))\noperation = response.get("id")\nif not isinstance(operation, str) or not operation: raise SystemExit("No actual original operation ID; preserve the response and do not resubmit")\nprint(quote(operation, safe=""))\nPY_ID\n)"\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID" \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -o batch-status-response.json\n
Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Bevar hele den opprinnelige statusresponsen i JSON, alle resultater og custom_id-verdier samt hele svar- eller feilinnholdet. Lagre fullførte results[] som JSONL uten filtrering.

Hvis det opprinnelige svaret må kontrolleres

Bevar den opprinnelige operasjons-ID-en. 503 result_pending_check har X-Should-Retry:false; send aldri den opprinnelige batchen på nytt når utfallet er ukjent.

Svarfelter
FeltType
Feltresults[].custom_idTypestring
Feltresults[].response.body.choices[].message.contentTypestring|null
Feltresults[].errorTypeobject|null
FeltusageTypeobject|null
FeltidTypestring
FeltmodelTypestring
FeltendpointTypestring
FeltstatusTypestring
Feltrequest_countsTypeobject
Feltresults[].idTypestring
Feltresults[].response.status_codeTypeinteger
Feltresults[].response.request_idTypestring
Feil og neste trinn
SvarVilkårNeste trinn
Svar400 · invalid_request_errorVilkårUgyldig struktur i det dokumenterte formatet med innebygde forespørsler, dupliserte nøkler, ugyldig elementidentitet eller konflikt med modellens konfigurerte funksjoner.Neste trinnRett de angitte feltene før du sender en ny forespørsel.
Svar401 · authentication_errorVilkårUgyldig API-nøkkel.Neste trinnBruk den autoriserte Ailoot-nøkkelen.
Svar403 · permission_errorVilkårGruppen for batchbehandling er ikke tilgjengelig.Neste trinnKontroller tilgangsrettighetene til nøkkelen/gruppen.
Svar422 · invalid_request_errorVilkårBatch belastes saldoen; opprettelse via abonnement avvises.Neste trinnBruk den autoriserte gruppen som belastes saldoen.
Svar422 · price_unavailableVilkårDet kan ikke beregnes en pris for batchens inndata.Neste trinnBevar svaret; bruk de dokumenterte inndataene for API-familien.
Svar402 · billing_errorVilkårBeløpsreservasjon for batchbehandling er ikke tilgjengelig.Neste trinnLøs problemet som hindrer forespørselen i å bli godkjent før du sender en ny forespørsel.
Svar503 · price_unavailableVilkårPris for Batch-metoden eller systemets innebygde satser er ikke tilgjengelige.Neste trinnBevar svaret; ikke erstatt prisene.
Svar503 · api_errorVilkårDen nøyaktige leverandørruten er ikke tilgjengelig.Neste trinnBevar svaret slik at ruten kan repareres.
Svar503 · result_pending_checkVilkårDet opprinnelige resultatet må kontrolleres; X-Should-Retry:false.Neste trinnBevar opprinnelig operation_id/id og les statusen; gjenta aldri den opprinnelige POST-forespørselen.
Svar404 · not_foundVilkårStatusoperasjonen for batchen finnes ikke eller tilhører en annen identitet.Neste trinnBruk nøyaktig den opprinnelige id-verdien og samme bruker/nøkkel/gruppe.

Aliaser

Modellaliaser

Ailoot Ultra openai/gpt-4.1-mini:batch

Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

Tilknyttede anroper-ID-er

openai/gpt-4.1-mini:batch

", "method_identity": { "effective_request_model_id": "openai/gpt-4.1-mini:batch", "fmt": "batches", "http": "POST", "path": "/v1/batches", "request_model_id": "openai/gpt-4.1-mini:batch", "route_label": "Ultra" }, "method_key": "Ultra|batches|/v1/batches|openai%2Fgpt-4.1-mini%3Abatch", "ordinal": 0, "rawMethod": { "available": null, "cache_read": 0.1, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Preserve full JSON and every result; provider real IDs are only read from actual returned responses.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "errors": [ { "code": null, "condition": "Ugyldig struktur i det dokumenterte formatet med innebygde forespørsler, dupliserte nøkler, ugyldig elementidentitet eller konflikt med modellens konfigurerte funksjoner.", "http_status": 400, "recovery": "Rett de angitte feltene før du sender en ny forespørsel.", "type": "invalid_request_error" }, { "code": null, "condition": "Ugyldig API-nøkkel.", "http_status": 401, "recovery": "Bruk den autoriserte Ailoot-nøkkelen.", "type": "authentication_error" }, { "code": null, "condition": "Gruppen for batchbehandling er ikke tilgjengelig.", "http_status": 403, "recovery": "Kontroller tilgangsrettighetene til nøkkelen/gruppen.", "type": "permission_error" }, { "code": null, "condition": "Batch belastes saldoen; opprettelse via abonnement avvises.", "http_status": 422, "recovery": "Bruk den autoriserte gruppen som belastes saldoen.", "type": "invalid_request_error" }, { "code": null, "condition": "Det kan ikke beregnes en pris for batchens inndata.", "http_status": 422, "recovery": "Bevar svaret; bruk de dokumenterte inndataene for API-familien.", "type": "price_unavailable" }, { "code": null, "condition": "Beløpsreservasjon for batchbehandling er ikke tilgjengelig.", "http_status": 402, "recovery": "Løs problemet som hindrer forespørselen i å bli godkjent før du sender en ny forespørsel.", "type": "billing_error" }, { "code": null, "condition": "Pris for Batch-metoden eller systemets innebygde satser er ikke tilgjengelige.", "http_status": 503, "recovery": "Bevar svaret; ikke erstatt prisene.", "type": "price_unavailable" }, { "code": null, "condition": "Den nøyaktige leverandørruten er ikke tilgjengelig.", "http_status": 503, "recovery": "Bevar svaret slik at ruten kan repareres.", "type": "api_error" }, { "code": "result_pending_check", "condition": "Det opprinnelige resultatet må kontrolleres; X-Should-Retry:false.", "http_status": 503, "recovery": "Bevar opprinnelig operation_id/id og les statusen; gjenta aldri den opprinnelige POST-forespørselen.", "type": null }, { "code": "not_found", "condition": "Statusoperasjonen for batchen finnes ikke eller tilhører en annen identitet.", "http_status": 404, "recovery": "Bruk nøyaktig den opprinnelige id-verdien og samme bruker/nøkkel/gruppe.", "type": null } ], "example_body": { "endpoint": "/v1/chat/completions", "model": "openai/gpt-4.1-mini:batch", "requests": [ { "body": { "max_tokens": 16, "messages": [ { "content": "Hello!", "role": "user" } ] }, "custom_id": "req-0001" } ] }, "input_constraints": [ "Use the exact shown :batch model ID.", "Each custom_id must be nonempty and unique within the batch.", "Keep requests last in the serialized body; duplicate JSON keys are rejected.", "Each body.model is omitted or equals the exact batch caller or its documented base ID.", "Per-item provider, service_tier and input_type are outside this batch profile.", "stream is omitted or false.", "Supply text messages for this Chat batch profile; image/audio/file/video objects, hosted tools and cache-control fields are outside this profile.", "If body.model is present, use only the exact caller or wire ID listed here; no suffix conversion is needed.", "For google/ wire IDs, all items use an identical response_format." ], "outputs": { "all_results": "Bevar hele den opprinnelige statusresponsen i JSON, alle resultater og custom_id-verdier samt hele svar- eller feilinnholdet. Lagre fullførte results[] som JSONL uten filtrering.", "enclosing_family": "batch", "family": "text", "fields": [ { "name": "results[].custom_id", "type": "string" }, { "name": "results[].response.body.choices[].message.content", "type": "string|null" }, { "name": "results[].error", "type": "object|null" }, { "name": "usage", "type": "object|null" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "endpoint", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "request_counts", "type": "object" }, { "description": null, "name": "results[].id", "type": "string" }, { "description": null, "name": "results[].response.status_code", "type": "integer" }, { "description": null, "name": "results[].response.request_id", "type": "string" } ], "format": "JSON fra results[].response.body direkte i svaret" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "/v1/chat/completions" ], "enum_known": true, "name": "endpoint", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "openai/gpt-4.1-mini:batch" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "requests", "required": true, "type": "batch_item[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "requests[].custom_id", "required": true, "type": "string", "unique_within_batch": true }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "requests[].body.messages", "required": true, "type": "message[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "24h" ], "enum_known": true, "name": "completion_window", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "object|null" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "openai/gpt-4.1-mini:batch", "openai/gpt-4.1-mini" ], "enum_known": true, "name": "requests[].body.model", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ [ "openai" ] ], "enum_known": true, "name": "provider.only", "required": false, "type": "string[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ false, null ], "enum_known": true, "name": "provider.allow_fallbacks", "required": false, "type": "boolean|null" } ], "provider_policy": { "allow_fallbacks": false, "configured_only": [ "openai" ], "per_item_override": false, "when_omitted": "Current Source injects the exact persisted declaration before fresh submission." }, "request_schema": { "additionalProperties": false, "properties": { "completion_window": { "enum": [ "24h" ], "type": "string" }, "endpoint": { "enum": [ "/v1/chat/completions" ], "type": "string" }, "model": { "enum": [ "openai/gpt-4.1-mini:batch" ], "type": "string" }, "provider": { "additionalProperties": false, "properties": { "allow_fallbacks": { "enum": [ false, null ], "type": [ "boolean", "null" ] }, "only": { "enum": [ [ "openai" ] ], "items": { "enum": [ "openai" ], "type": "string" }, "maxItems": 1, "minItems": 1, "type": "array" } }, "type": [ "object", "null" ] }, "requests": { "items": { "additionalProperties": false, "properties": { "body": { "additionalProperties": true, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "properties": { "content": { "type": "string" }, "role": { "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "openai/gpt-4.1-mini:batch", "openai/gpt-4.1-mini" ], "type": "string" } }, "required": [ "messages" ], "type": "object" }, "custom_id": { "minLength": 1, "type": "string" } }, "required": [ "custom_id", "body" ], "type": "object" }, "minItems": 1, "type": "array" } }, "required": [ "endpoint", "model", "requests" ], "type": "object" }, "schema_template": { "endpoint": "/v1/chat/completions", "model": "openai/gpt-4.1-mini:batch", "requests": [ { "body": { "max_tokens": 16, "messages": [ { "content": "Hello!", "role": "user" } ] }, "custom_id": "req-0001" } ] }, "unsupported": [ "Files/input_file_id batch upload workflow", "active cancel route", "public batch list/delete/result-download route", "model-name-derived capability or weights equivalence" ] }, "input": { "content_type": "application/json", "file_material": "Klienten kan lese det faktiske UTF-8-kodede JSONL-innholdet lokalt inn i requests[]. Feltet purpose for opplasting, input_file_id og filreferanser brukes ikke. Manglende eller tomt kundemateriale stopper klargjøringen før POST.", "material_types": [ "text" ], "optional_controls": [ "provider.only", "provider.allow_fallbacks", "completion_window" ], "representation": "requests[] direkte i forespørselen; hvert element har custom_id og body", "request_endpoint_profile": "/v1/chat/completions", "required": [ "endpoint", "model", "requests" ], "schema_scope": "Forespørselsinnhold for tekstbasert Chat Completions lagt direkte inn i det dokumenterte Batch-formatet.", "serialization_order": [ "endpoint", "model", "provider (hvis angitt)", "completion_window (hvis angitt)", "requests til slutt" ] }, "lifecycle": { "cancel": null, "create": { "accepted_status": 202, "http": "POST", "path": "/v1/batches" }, "delete": null, "file_upload": null, "mode": "asynchronous", "observed_status_values": [ "validating", "in_progress", "finalizing", "completed", "failed", "expired", "cancelling", "cancelled" ], "owned_results": { "behavior": "Completed results are saved as owned JSONL, read back byte-for-byte and registered in the existing media library before publication after settlement. Status returns inline results; no separate Batch download route is added.", "format": "application/x-ndjson", "public_url_field_in_status": null }, "status": { "http": "GET", "id_source": "faktisk response.id fra den opprinnelige opprettelsen; samme bruker/nøkkel/gruppe", "path": "/v1/batches/{operation_id}" }, "terminal": [ "completed", "failed", "expired", "cancelled" ], "unknown": "Bevar den opprinnelige operasjons-ID-en. 503 result_pending_check har X-Should-Retry:false; send aldri den opprinnelige batchen på nytt når utfallet er ukjent." }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/batches" }, "output": { "all_results": "Preserve the full original status JSON, every result/custom_id and complete response or error body. Save completed results[] as JSONL without filtering.", "family": "batch", "format": "JSON; completed results[] are returned inline and can be saved as JSONL." } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Grunnpriser for tokener", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Nivå 1 for forespørselslengde", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{\"endpoint\":\"/v1/chat/completions\",\"model\":\"openai/gpt-4.1-mini:batch\",\"requests\":[{\"custom_id\":\"req-0001\",\"body\":{\"messages\":[{\"role\":\"user\",\"content\":\"Hello!\"}],\"max_tokens\":16}}]}')\nPath(\"batch-request.json\").write_text(json.dumps(body,ensure_ascii=False),encoding=\"utf-8\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\n", "label": "curl · retained fixture", "language": "bash" }, { "code": "import json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n path = Path(customer_path)\n if not path.is_file(): raise ValueError(\"Customer JSONL file is missing\")\n items = [json.loads(line) for line in path.read_text(encoding=\"utf-8\").splitlines() if line.strip()]\n if not items: raise ValueError(\"Customer JSONL contains no requests\")\n ids = set()\n for item in items:\n if set(item) != {\"custom_id\", \"body\"}: raise ValueError(\"Each item needs custom_id and body\")\n cid = item[\"custom_id\"]\n if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError(\"custom_id must be nonempty and unique\")\n ids.add(cid)\n if not isinstance(item[\"body\"], dict) or not item[\"body\"].get(\"messages\"): raise ValueError(\"Supply actual text messages\")\n supplied_model = item[\"body\"].get(\"model\")\n if supplied_model is not None and supplied_model not in ['openai/gpt-4.1-mini:batch', 'openai/gpt-4.1-mini']: raise ValueError(\"body.model must be an exact documented caller or wire ID\")\n return {\"endpoint\":\"/v1/chat/completions\", \"model\":\"openai/gpt-4.1-mini:batch\", \"requests\":items}\n\nif __name__ == \"__main__\":\n material = os.environ.get(\"AILOOT_BATCH_REQUESTS_JSONL\", \"\")\n if not material: raise SystemExit(\"Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file\")\n body = prepare_requests(material)\n key = os.environ.get(\"AILOOT_API_KEY\", \"\")\n if not key: raise SystemExit(\"Set AILOOT_API_KEY\")\n request = Request(\"https://api.ailoot.ai/v1/batches\", data=json.dumps(body, ensure_ascii=False).encode(\"utf-8\"), headers={\"Authorization\":\"Bearer \" + key, \"Content-Type\":\"application/json\"}, method=\"POST\")\n with urlopen(request) as response:\n raw = response.read()\n Path(\"batch-create-response.json\").write_bytes(raw)\n print(raw.decode(\"utf-8\"))\n", "label": "Python HTTP · actual customer JSONL", "language": "python" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nBATCH_OPERATION_ID=\"$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path(\"batch-create-response.json\").read_text(encoding=\"utf-8\"))\noperation = response.get(\"id\")\nif not isinstance(operation, str) or not operation: raise SystemExit(\"No actual original operation ID; preserve the response and do not resubmit\")\nprint(quote(operation, safe=\"\"))\nPY_ID\n)\"\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID\" \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -o batch-status-response.json\n", "label": "curl · original operation status", "language": "bash" }, { "code": "import json\nfrom pathlib import Path\nraw = Path(\"batch-status-response.json\").read_bytes()\nresponse = json.loads(raw)\nif response.get(\"status\") != \"completed\":\n raise SystemExit(\"Keep the original operation; read its status without resubmitting\")\nresults = response.get(\"results\")\nif not isinstance(results, list) or not results:\n raise SystemExit(\"Preserve the original response; completed results are missing\")\nPath(\"batch-results.jsonl\").write_text(\"\".join(json.dumps(item, ensure_ascii=False) + \"\\n\" for item in results), encoding=\"utf-8\")\n# Preserve batch-status-response.json with aggregate usage and every result/error.\n", "label": "Python · save every completed result", "language": "python" } ], "family": "batch", "fast_multiplier": null, "flex_multiplier": null, "fmt": "batches", "hints": [ "Read your actual request items before submission; inline requests are required.", "Keep the returned operation ID and every result. Never replay an unknown submission." ], "http": "POST", "in": 0.4, "input": [ "text" ], "label": "Batchbehandling", "max_out": null, "max_reasoning_effort_multiplier": null, "out": 1.6, "output": [ "text" ], "path": "/v1/batches", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "openai/gpt-4.1-mini:batch", "route_label": "Ultra", "status_reads": [ "GET /v1/batches/{operation_id}" ], "tiers": [ { "cache_read": 0.1, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.4, "input_multiplier": null, "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "out": 1.6, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } } ], "model_id": "openai/gpt-4.1-mini:batch", "nativeProvenance": { "input_facts_canonical_sha256": "623fb26451ebe3b3b5e4123a456593c88ce707e6bbed844a6c4e6f25873c6621", "input_html_sha256": "3f2753c6d808cee95a5958088fd28e45f838d61dc80ff938aa6db908e8665138", "private_audit_sha256": "d78de62ea242566d8217359b1917121ca0b82d9d806b2f4e467f0590e176dc1e", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/nb/openai-gpt-4-1-mini-u003a-batch/", "description": "Batch for uavhengig tekst med custom_id-kobling og valgfritt 24h-fullføringsvindu.", "locale": "nb", "md_url": "https://ailoot.ai/models/nb/openai-gpt-4-1-mini-u003a-batch/index.md", "title": "OpenAI: GPT-4.1 Mini (batch) — Ailoot", "url": "https://ailoot.ai/models/nb/openai-gpt-4-1-mini-u003a-batch/" }, "rawModel": { "about": "GPT-4.1 Mini er OpenAIs mindre og raskere GPT-4.1-modell for instruksjonsfølging og verktøykall. Den tar imot tekst og bilder og returnerer tekst, inkludert skjemabaserte Structured Outputs. Produsenten beskriver svar med lav forsinkelse uten et separat resonneringstrinn, noe som gjør Mini nyttig for en interaktiv assistent eller et klart spesifisert steg i en større arbeidsflyt.\n\nFor uthenting fra dokumenter oppgir du kildematerialet, navngir feltene som skal returneres og forklarer hvordan en manglende eller motstridende verdi skal se ut. En praktisk oppgave er å gjøre et sett med støttemeldinger om til et tema, et sammendrag av underlaget og et svarforslag forankret i de relevante retningslinjene. For en kodeendring tar du med den berørte filen, den ønskede endringen og oppførselen som må bevares. Disse oppgavebeskrivelsene gir modellen et konkret produkt å lage fremfor en åpen instruksjon om å analysere alt.\n\nOpenAI angir et kontekstvindu på 1047576 tokener, en maksimal utdatamengde på 32768 tokener og en kunnskapsgrense på 1. juni 2024. Kildematerialet, samtalen og de genererte utdataene deler den tilgjengelige konteksten. Organiser lange inndata med dokumentgrenser og identifikatorer, angi spørsmålet som betyr noe og gi plass til svaret. Oppdaterte eller private fakta hører hjemme i materialet du gir eller i resultatene fra et uttrykkelig konfigurert søkeverktøy.\n\nBildeinndata støtter spørsmål om et fotografi, skjermbilde, diagram eller en dokumentside. OpenAIs bildeveiledning godtar PNG, JPEG, WebP og ikke-animert GIF. Den nåværende størrelsestabellen for GPT-4.1 Mini støtter detaljnivåene low, high og auto med den samme maksimale dimensjonen på 2048 piksler og et skaleringsbudsjett på 6144 bildepatcher; detaljnivået original støttes ikke. Forstørr liten tekst, hold etiketter rettvendte og bevar den visuelle konteksten som trengs for å tolke et diagram. Presise romlige forhold, antall gjenstander og noe tekst utenfor det latinske alfabetet kan være vanskelig, så be om den relevante observasjonen og bevar bildet for sammenligning. I OpenAIs dokumenterte bildearbeidsflyt er forespørselens samlede datamengde begrenset til 512 MB, og en forespørsel kan inneholde opptil 1500 bilder; bildene og teksten må også passe i modellens kontekst.\n\nProdusentens arbeidsflyt for filinndata skiller PDF-sider fra andre dokumenter. Med en modell som støtter bilder, bidrar PDF-filer med uthentet tekst og sidebilder. Dokumenter som ikke er PDF, bidrar med tekst fremfor innebygde diagrammer, mens regnearkbehandling bruker opptil de første 1000 radene i hvert ark med en mindre, utvidet representasjon. Hver fil må være under 50 MB, og samlet tillatt filstørrelse per forespørsel er 50 MB. Chat Completions godtar PDF-fildeler; Responses-arbeidsflyten godtar også de dokumenterte tekst-, kontordokument- og regnearkformatene. Velg representasjonen som inneholder underlaget spørsmålet ditt trenger.\n\nStrømming kan returnere tekst etter hvert som den genereres. For et endelig maskinlesbart produkt begrenser Structured Outputs et fullført svar til det støttede delsettet av JSON Schema, mens JSON-modus bare gjelder JSON-gyldighet. Definer nødvendige felter, typer og tillatte verdier og representer manglende informasjon uttrykkelig. Et avslag eller et ufullstendig svar trenger separat håndtering, og et objekt med korrekt form kan fortsatt inneholde feil verdier. Det nyttige resultatet er et fullstendig sett med felter knyttet til underlaget du har gitt.\n\nMinis dokumenterte verktøysett inkluderer funksjonskall, nettsøk, filsøk, kodetolkning og MCP-tilkoblinger. Oppgi klare beskrivelser og argumentskjemaer for egendefinerte verktøy; applikasjonen utfører forespurte funksjoner og returnerer faktiske observasjoner for modellens neste steg. OpenAI inkluderer også Mini blant modeller som kan bruke bildegenereringsverktøyet i en konfigurert Responses-arbeidsflyt. Det verktøyet produserer et separat bildeprodukt; Minis egen dokumenterte utdatamodalitet er fortsatt tekst. Et søke- eller beregningsresultat bør inneholde faktaene som trengs for den endelige forklaringen.\n\nPredicted Outputs er en separat produsentvei for å generere stort sett kjent tekst eller kode på nytt med små endringer. Oppgi det eksisterende innholdet sammen med endringen du trenger. Denne veien bruker bare tekst og kan ikke kombineres med funksjonskall; den utelukker også flere vanlige genereringskontroller, inkludert max_completion_tokens og logprobs. Bruk en vanlig forespørsel som benytter verktøy når oppgaven trenger eksterne observasjoner, fremfor å behandle prediksjon og verktøyutførelse som utbyttbare.\n\nOpenAI dokumenterer veiledet finjustering og direkte preferanseoptimalisering for GPT-4.1 Mini-familiens navngitte modellversjon. Dette er arbeidsflyter for modelltilpasning: veiledede eksempler lærer ønsket oppførsel fra inndata til utdata, mens foretrukne og avviste svar uttrykker et valg av stil eller innhold. For vanlig inferens begynner du med en tydelig oppgave, relevant underlag og ett eksempel på det nødvendige resultatet. En avgrenset oppfølging kan korrigere et felt, forbedre et svarforslag eller revidere den samme kodeendringen samtidig som de opprinnelige begrensningene holdes synlige.", "alias_of": null, "aliases": [], "author": "OpenAI", "capabilities": { "context_length": 1047576, "manufacturer_input": [ "image", "text", "file" ], "manufacturer_output": [ "text" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" } ], "summary": "Fullstendige priser for konfigurasjonen finnes i detaljene." } ], "ctx": null, "formats": [ "batches" ], "id": "openai/gpt-4.1-mini:batch", "input": [ "text" ], "kind": "text", "max_out": null, "methods": [ { "available": null, "cache_read": 0.1, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Preserve full JSON and every result; provider real IDs are only read from actual returned responses.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "errors": [ { "code": null, "condition": "Ugyldig struktur i det dokumenterte formatet med innebygde forespørsler, dupliserte nøkler, ugyldig elementidentitet eller konflikt med modellens konfigurerte funksjoner.", "http_status": 400, "recovery": "Rett de angitte feltene før du sender en ny forespørsel.", "type": "invalid_request_error" }, { "code": null, "condition": "Ugyldig API-nøkkel.", "http_status": 401, "recovery": "Bruk den autoriserte Ailoot-nøkkelen.", "type": "authentication_error" }, { "code": null, "condition": "Gruppen for batchbehandling er ikke tilgjengelig.", "http_status": 403, "recovery": "Kontroller tilgangsrettighetene til nøkkelen/gruppen.", "type": "permission_error" }, { "code": null, "condition": "Batch belastes saldoen; opprettelse via abonnement avvises.", "http_status": 422, "recovery": "Bruk den autoriserte gruppen som belastes saldoen.", "type": "invalid_request_error" }, { "code": null, "condition": "Det kan ikke beregnes en pris for batchens inndata.", "http_status": 422, "recovery": "Bevar svaret; bruk de dokumenterte inndataene for API-familien.", "type": "price_unavailable" }, { "code": null, "condition": "Beløpsreservasjon for batchbehandling er ikke tilgjengelig.", "http_status": 402, "recovery": "Løs problemet som hindrer forespørselen i å bli godkjent før du sender en ny forespørsel.", "type": "billing_error" }, { "code": null, "condition": "Pris for Batch-metoden eller systemets innebygde satser er ikke tilgjengelige.", "http_status": 503, "recovery": "Bevar svaret; ikke erstatt prisene.", "type": "price_unavailable" }, { "code": null, "condition": "Den nøyaktige leverandørruten er ikke tilgjengelig.", "http_status": 503, "recovery": "Bevar svaret slik at ruten kan repareres.", "type": "api_error" }, { "code": "result_pending_check", "condition": "Det opprinnelige resultatet må kontrolleres; X-Should-Retry:false.", "http_status": 503, "recovery": "Bevar opprinnelig operation_id/id og les statusen; gjenta aldri den opprinnelige POST-forespørselen.", "type": null }, { "code": "not_found", "condition": "Statusoperasjonen for batchen finnes ikke eller tilhører en annen identitet.", "http_status": 404, "recovery": "Bruk nøyaktig den opprinnelige id-verdien og samme bruker/nøkkel/gruppe.", "type": null } ], "example_body": { "endpoint": "/v1/chat/completions", "model": "openai/gpt-4.1-mini:batch", "requests": [ { "body": { "max_tokens": 16, "messages": [ { "content": "Hello!", "role": "user" } ] }, "custom_id": "req-0001" } ] }, "input_constraints": [ "Use the exact shown :batch model ID.", "Each custom_id must be nonempty and unique within the batch.", "Keep requests last in the serialized body; duplicate JSON keys are rejected.", "Each body.model is omitted or equals the exact batch caller or its documented base ID.", "Per-item provider, service_tier and input_type are outside this batch profile.", "stream is omitted or false.", "Supply text messages for this Chat batch profile; image/audio/file/video objects, hosted tools and cache-control fields are outside this profile.", "If body.model is present, use only the exact caller or wire ID listed here; no suffix conversion is needed.", "For google/ wire IDs, all items use an identical response_format." ], "outputs": { "all_results": "Bevar hele den opprinnelige statusresponsen i JSON, alle resultater og custom_id-verdier samt hele svar- eller feilinnholdet. Lagre fullførte results[] som JSONL uten filtrering.", "enclosing_family": "batch", "family": "text", "fields": [ { "name": "results[].custom_id", "type": "string" }, { "name": "results[].response.body.choices[].message.content", "type": "string|null" }, { "name": "results[].error", "type": "object|null" }, { "name": "usage", "type": "object|null" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "endpoint", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "request_counts", "type": "object" }, { "description": null, "name": "results[].id", "type": "string" }, { "description": null, "name": "results[].response.status_code", "type": "integer" }, { "description": null, "name": "results[].response.request_id", "type": "string" } ], "format": "JSON fra results[].response.body direkte i svaret" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "/v1/chat/completions" ], "enum_known": true, "name": "endpoint", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "openai/gpt-4.1-mini:batch" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "requests", "required": true, "type": "batch_item[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "requests[].custom_id", "required": true, "type": "string", "unique_within_batch": true }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "requests[].body.messages", "required": true, "type": "message[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "24h" ], "enum_known": true, "name": "completion_window", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "object|null" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "openai/gpt-4.1-mini:batch", "openai/gpt-4.1-mini" ], "enum_known": true, "name": "requests[].body.model", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ [ "openai" ] ], "enum_known": true, "name": "provider.only", "required": false, "type": "string[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ false, null ], "enum_known": true, "name": "provider.allow_fallbacks", "required": false, "type": "boolean|null" } ], "provider_policy": { "allow_fallbacks": false, "configured_only": [ "openai" ], "per_item_override": false, "when_omitted": "Current Source injects the exact persisted declaration before fresh submission." }, "request_schema": { "additionalProperties": false, "properties": { "completion_window": { "enum": [ "24h" ], "type": "string" }, "endpoint": { "enum": [ "/v1/chat/completions" ], "type": "string" }, "model": { "enum": [ "openai/gpt-4.1-mini:batch" ], "type": "string" }, "provider": { "additionalProperties": false, "properties": { "allow_fallbacks": { "enum": [ false, null ], "type": [ "boolean", "null" ] }, "only": { "enum": [ [ "openai" ] ], "items": { "enum": [ "openai" ], "type": "string" }, "maxItems": 1, "minItems": 1, "type": "array" } }, "type": [ "object", "null" ] }, "requests": { "items": { "additionalProperties": false, "properties": { "body": { "additionalProperties": true, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "properties": { "content": { "type": "string" }, "role": { "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "openai/gpt-4.1-mini:batch", "openai/gpt-4.1-mini" ], "type": "string" } }, "required": [ "messages" ], "type": "object" }, "custom_id": { "minLength": 1, "type": "string" } }, "required": [ "custom_id", "body" ], "type": "object" }, "minItems": 1, "type": "array" } }, "required": [ "endpoint", "model", "requests" ], "type": "object" }, "schema_template": { "endpoint": "/v1/chat/completions", "model": "openai/gpt-4.1-mini:batch", "requests": [ { "body": { "max_tokens": 16, "messages": [ { "content": "Hello!", "role": "user" } ] }, "custom_id": "req-0001" } ] }, "unsupported": [ "Files/input_file_id batch upload workflow", "active cancel route", "public batch list/delete/result-download route", "model-name-derived capability or weights equivalence" ] }, "input": { "content_type": "application/json", "file_material": "Klienten kan lese det faktiske UTF-8-kodede JSONL-innholdet lokalt inn i requests[]. Feltet purpose for opplasting, input_file_id og filreferanser brukes ikke. Manglende eller tomt kundemateriale stopper klargjøringen før POST.", "material_types": [ "text" ], "optional_controls": [ "provider.only", "provider.allow_fallbacks", "completion_window" ], "representation": "requests[] direkte i forespørselen; hvert element har custom_id og body", "request_endpoint_profile": "/v1/chat/completions", "required": [ "endpoint", "model", "requests" ], "schema_scope": "Forespørselsinnhold for tekstbasert Chat Completions lagt direkte inn i det dokumenterte Batch-formatet.", "serialization_order": [ "endpoint", "model", "provider (hvis angitt)", "completion_window (hvis angitt)", "requests til slutt" ] }, "lifecycle": { "cancel": null, "create": { "accepted_status": 202, "http": "POST", "path": "/v1/batches" }, "delete": null, "file_upload": null, "mode": "asynchronous", "observed_status_values": [ "validating", "in_progress", "finalizing", "completed", "failed", "expired", "cancelling", "cancelled" ], "owned_results": { "behavior": "Completed results are saved as owned JSONL, read back byte-for-byte and registered in the existing media library before publication after settlement. Status returns inline results; no separate Batch download route is added.", "format": "application/x-ndjson", "public_url_field_in_status": null }, "status": { "http": "GET", "id_source": "faktisk response.id fra den opprinnelige opprettelsen; samme bruker/nøkkel/gruppe", "path": "/v1/batches/{operation_id}" }, "terminal": [ "completed", "failed", "expired", "cancelled" ], "unknown": "Bevar den opprinnelige operasjons-ID-en. 503 result_pending_check har X-Should-Retry:false; send aldri den opprinnelige batchen på nytt når utfallet er ukjent." }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/batches" }, "output": { "all_results": "Preserve the full original status JSON, every result/custom_id and complete response or error body. Save completed results[] as JSONL without filtering.", "family": "batch", "format": "JSON; completed results[] are returned inline and can be saved as JSONL." } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Grunnpriser for tokener", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Nivå 1 for forespørselslengde", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{\"endpoint\":\"/v1/chat/completions\",\"model\":\"openai/gpt-4.1-mini:batch\",\"requests\":[{\"custom_id\":\"req-0001\",\"body\":{\"messages\":[{\"role\":\"user\",\"content\":\"Hello!\"}],\"max_tokens\":16}}]}')\nPath(\"batch-request.json\").write_text(json.dumps(body,ensure_ascii=False),encoding=\"utf-8\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\n", "label": "curl · retained fixture", "language": "bash" }, { "code": "import json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n path = Path(customer_path)\n if not path.is_file(): raise ValueError(\"Customer JSONL file is missing\")\n items = [json.loads(line) for line in path.read_text(encoding=\"utf-8\").splitlines() if line.strip()]\n if not items: raise ValueError(\"Customer JSONL contains no requests\")\n ids = set()\n for item in items:\n if set(item) != {\"custom_id\", \"body\"}: raise ValueError(\"Each item needs custom_id and body\")\n cid = item[\"custom_id\"]\n if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError(\"custom_id must be nonempty and unique\")\n ids.add(cid)\n if not isinstance(item[\"body\"], dict) or not item[\"body\"].get(\"messages\"): raise ValueError(\"Supply actual text messages\")\n supplied_model = item[\"body\"].get(\"model\")\n if supplied_model is not None and supplied_model not in ['openai/gpt-4.1-mini:batch', 'openai/gpt-4.1-mini']: raise ValueError(\"body.model must be an exact documented caller or wire ID\")\n return {\"endpoint\":\"/v1/chat/completions\", \"model\":\"openai/gpt-4.1-mini:batch\", \"requests\":items}\n\nif __name__ == \"__main__\":\n material = os.environ.get(\"AILOOT_BATCH_REQUESTS_JSONL\", \"\")\n if not material: raise SystemExit(\"Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file\")\n body = prepare_requests(material)\n key = os.environ.get(\"AILOOT_API_KEY\", \"\")\n if not key: raise SystemExit(\"Set AILOOT_API_KEY\")\n request = Request(\"https://api.ailoot.ai/v1/batches\", data=json.dumps(body, ensure_ascii=False).encode(\"utf-8\"), headers={\"Authorization\":\"Bearer \" + key, \"Content-Type\":\"application/json\"}, method=\"POST\")\n with urlopen(request) as response:\n raw = response.read()\n Path(\"batch-create-response.json\").write_bytes(raw)\n print(raw.decode(\"utf-8\"))\n", "label": "Python HTTP · actual customer JSONL", "language": "python" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nBATCH_OPERATION_ID=\"$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path(\"batch-create-response.json\").read_text(encoding=\"utf-8\"))\noperation = response.get(\"id\")\nif not isinstance(operation, str) or not operation: raise SystemExit(\"No actual original operation ID; preserve the response and do not resubmit\")\nprint(quote(operation, safe=\"\"))\nPY_ID\n)\"\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID\" \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -o batch-status-response.json\n", "label": "curl · original operation status", "language": "bash" }, { "code": "import json\nfrom pathlib import Path\nraw = Path(\"batch-status-response.json\").read_bytes()\nresponse = json.loads(raw)\nif response.get(\"status\") != \"completed\":\n raise SystemExit(\"Keep the original operation; read its status without resubmitting\")\nresults = response.get(\"results\")\nif not isinstance(results, list) or not results:\n raise SystemExit(\"Preserve the original response; completed results are missing\")\nPath(\"batch-results.jsonl\").write_text(\"\".join(json.dumps(item, ensure_ascii=False) + \"\\n\" for item in results), encoding=\"utf-8\")\n# Preserve batch-status-response.json with aggregate usage and every result/error.\n", "label": "Python · save every completed result", "language": "python" } ], "family": "batch", "fast_multiplier": null, "flex_multiplier": null, "fmt": "batches", "hints": [ "Read your actual request items before submission; inline requests are required.", "Keep the returned operation ID and every result. Never replay an unknown submission." ], "http": "POST", "in": 0.4, "input": [ "text" ], "label": "Batchbehandling", "max_out": null, "max_reasoning_effort_multiplier": null, "out": 1.6, "output": [ "text" ], "path": "/v1/batches", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "openai/gpt-4.1-mini:batch", "route_label": "Ultra", "status_reads": [ "GET /v1/batches/{operation_id}" ], "tiers": [ { "cache_read": 0.1, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.4, "input_multiplier": null, "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "out": 1.6, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.0004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000004", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0.0016000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.0000016", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0.0000001", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "model_aliases": [ { "canonical_model_id": "openai/gpt-4.1-mini:batch", "request_model_id": "openai/gpt-4.1-mini:batch", "route_label": "Ultra" } ], "name": "OpenAI: GPT-4.1 Mini (batch)", "price": { "in": 0.4, "in_label": null, "out": 1.6, "out_label": null, "scope_label": "Token rates", "sort_in": 0.4, "sort_out": 1.6, "varies": true }, "short": "GPT-4.1 Mini kombinerer tekst- og bildeforståelse med stor kontekst, presise instruksjoner og verktøykall. Bruk den til å hente ut strukturert informasjon, svare ut fra dokumentene du gir eller utføre en avgrenset skrive- og programmeringsoppgave." }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Batch for uavhengig tekst med custom_id-kobling og valgfritt 24h-fullføringsvindu.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "1d6a70e4eb0e3c38874f074604a44f3ac5064b6b5321fba07beabc637bed7268", "renderer_sha256": "c8cb5a92c10b47373d294dee7465d66796cd4710c6626fd81459dc0625fc6d26" }, "sourceRevision": "0798ec8092fea9dd7bdc2cbf7820975c1792f0bf44033d03003881227e0261a4" }