{"uid":"cap_nZMOrINrMGaB3hLA08RMF","slug":"agents-zerogpu-ai-zerogpu-single-input-inference-text-generation-65a12bf9","name":"ZeroGPU Single-Input Inference (Text Generation, Extraction, Classification)","description":"OpenAI-style Responses endpoint, authenticated by verifying the\n`zc-signature` HMAC over the raw request bytes. The request is routed by\n`model` using model metadata, and the same orchestration as\n`/v1/responses` runs behind it.\n\nOn success, actual token usage is settled with ZeroClick and reported\nvia the `zc-usage` response header.\n","url":"https://agents.zerogpu.ai/zeroclick/v1/responses?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["model","input"],"properties":{"text":{"type":"object","properties":{"format":{"type":"object","properties":{"type":{"enum":["text"],"type":"string","description":"Output format. `text` is supported; `json` is currently rejected."}}}}},"input":{"type":"string","description":"Prompt text. Combined with `instructions` (as a system message) to form the model input."},"model":{"type":"string","example":"LFM2.5-1.2B-Instruct"},"store":{"type":"boolean","default":true},"top_p":{"type":"number","nullable":true},"metadata":{"type":"object","description":"Up to 16 string key/value pairs echoed back in the response envelope. Also carries GLiNER usecase options (`usecase`, `schema`, `labels`, `threshold`, `mask`, `replacement_char`), which are consumed and not necessarily echoed.","additionalProperties":{"type":"string"}},"categories":{"type":"array","items":{"type":"string"},"description":"Candidate labels for text-classification models."},"truncation":{"enum":["auto","disabled"],"type":"string","default":"auto"},"temperature":{"type":"number","nullable":true},"instructions":{"type":"string","description":"System-style instructions prepended to the input. Classification models may pass comma-separated or bracketed candidate labels here."},"multilingual":{"type":"boolean"},"max_output_tokens":{"type":"integer","nullable":true},"parallel_tool_calls":{"type":"boolean","default":true},"previous_response_id":{"type":"string","nullable":true}},"additionalProperties":true},"responseSchema":{"type":"object","properties":{"id":{"type":"string"},"text":{"type":"object","properties":{"format":{"type":"object","properties":{"type":{"type":"string"}}}}},"user":{"type":"string","nullable":true},"error":{"oneOf":[{"type":"null"},{"type":"object","required":["message"],"properties":{"code":{"type":"string"},"type":{"type":"string"},"param":{"type":"string"},"message":{"type":"string"}},"description":"Error attached to a Responses envelope. OpenAI's ResponseError carries\n`code` and `message`; `type` and `param` are also emitted by some error\nsites on this endpoint.\n"}]},"model":{"type":"string"},"store":{"type":"boolean"},"tools":{"type":"array","items":{}},"top_p":{"type":"number","nullable":true},"usage":{"type":"object","nullable":true,"properties":{"input_tokens":{"type":"integer"},"total_tokens":{"type":"integer"},"output_tokens":{"type":"integer"},"input_tokens_details":{"type":"object","properties":{"cached_tokens":{"type":"integer"}}},"output_tokens_details":{"type":"object","properties":{"reasoning_tokens":{"type":"integer"}}}}},"object":{"type":"string","const":"response"},"output":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"role":{"type":"string","const":"assistant"},"type":{"type":"string","const":"message"},"status":{"type":"string"},"content":{"type":"array","items":{"type":"object","properties":{"text":{"type":"string"},"type":{"type":"string","const":"output_text"},"annotations":{"type":"array","items":{}}}}}}}},"status":{"enum":["completed","failed"],"type":"string"},"metadata":{"type":"object","additionalProperties":{"type":"string"}},"reasoning":{"type":"object","properties":{"effort":{"nullable":true},"summary":{"nullable":true}}},"created_at":{"type":"integer"},"truncation":{"enum":["auto","disabled"],"type":"string"},"temperature":{"type":"number","nullable":true},"tool_choice":{"type":"string"},"completed_at":{"type":"integer","nullable":true},"instructions":{"type":"string","nullable":true},"max_output_tokens":{"type":"integer","nullable":true},"incomplete_details":{"nullable":true},"parallel_tool_calls":{"type":"boolean"},"previous_response_id":{"type":"string","nullable":true}},"description":"OpenAI Responses `response` object. On error, `status` is `failed` and `error` is populated.","additionalProperties":true},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"unknown","displayCostAsset":"USD","priceDynamic":true,"priceHint":null,"priceStatus":"unknown_unparsed","priceSource":"registry","requiresHandshake":false,"reviewCount":2,"rating":{"score":"0.96","successRate":"0.66","reviews":2,"stars":"4.8","state":"rated"},"availabilityStatus":"healthy","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"unknown","summary":"price unknown","primary":{"kind":"dynamic","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"},"accepted":[{"kind":"dynamic","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"}]},"paymentMethods":[{"uid":"pm_fOmjnaKevLD5lQXoNRBnn","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"unknown","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"agents.zerogpu.ai","brandSlug":"agents-zerogpu-ai-x402","brandBaseUrl":"https://agents.zerogpu.ai","brandDocsUrl":null,"whatItDoes":"Sends a single input text to a selected ZeroGPU model and returns generated text, extracted entities/PII, or a classification label depending on the chosen model.","exampleAgentPrompt":"Use the gliner-multi-pii-v1 model to scan this text for PII across all entity types and return what you find: 'John Smith, born 12/03/1985, lives at 42 Maple Street, London, and his email is jsmith@email.com.'","exampleUseCases":[{"title":"PII detection in user-submitted content","prompt":"Scan this support ticket for any personal information like names, emails, phone numbers, or addresses using gliner-multi-pii-v1: 'Hi, I'm Sarah Connor, my account email is sarah.connor@gmail.com and my phone is +1-555-234-9876. Please help me reset my password.'"},{"title":"IAB content taxonomy classification","prompt":"Classify this article snippet into IAB content categories using zlm-v2-iab-classify-edge-enriched: 'The new iPhone 16 Pro features a 48MP camera system and a faster A18 chip, making it Apple's most advanced smartphone to date.'"},{"title":"Fast text generation for a chatbot response","prompt":"Using the llama-3.1-8b-instruct-fast model, generate a friendly two-sentence reply to this customer message with the instruction to keep it professional: 'I've been waiting 3 days for my order and haven't received any shipping updates.'"}],"resultDescription":"An OpenAI Responses-style object containing: an output array with the model's response (generated text, extracted entity list, or classification labels), the model name, creation timestamp, status ('completed' or 'failed'), and token usage breakdown (input_tokens, output_tokens, total_tokens). On error, status is 'failed' and an error field is populated.","failureModes":["Invalid or unsupported model ID returns an error status","Empty or missing input field causes a validation error","Instructions field provided to a classifier model is silently ignored","Token limits exceeded for large inputs may return a failed status","Unknown pricing or billing issues may result in a 402 Payment Required response","Network or infrastructure errors at the edge may cause transient failures"],"whenToPreferThis":"Choose this endpoint when you need a single-call, single-input inference without managing a messages array — ideal for classification, extraction, or short text generation tasks. Prefer it over the chat completions endpoint when working with extraction models (gliner2-base-v1, gliner-multi-pii-v1) or classification models (deberta-v3-small, IAB taxonomy models) that don't require conversational turn history. It is especially well-suited for high-volume pipelines processing one text at a time with specialized small models optimized for edge deployment.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":266,"lastUsedAt":"2026-10-02T01:14:46.347Z","lastSuccessfullyRanAt":"2026-10-02T01:14:46.347Z","lastHealthCheckAt":"2026-10-12T18:37:27.067Z","isFirstParty":false,"canonicalSlug":"agents-zerogpu-ai-zerogpu-single-input-inference-text-generation-65a12bf9"}