{"openapi":"3.1.0","jsonSchemaDialect":"https://json-schema.org/draft/2020-12/schema","info":{"title":"Doitong Models API","version":"2026-10-20","summary":"Image, video, audio and other AI models behind one REST interface, priced like the upstream in USD.","description":"One POST /run/{model} for every model (add ?wait= to get the result in the same call), one GET /requests/{id} for status, exact prices from POST /quote/{model}, output files on our storage (kept forever, paid per GB-month, or 7 days for free: the account setting or ?storage=) and signed webhooks. Model ids contain slashes; they are written as is in the path. Prices are API credits paid from the account's API balance: 1000 API credits = 1 USD, every price object carries the USD amount (add ?currency=rub for roubles). Typed per-model paths: this document carries the featured models by default; add ?category=<id>, ?model=<id> or ?models=all for others (the generic /run/{model_id} accepts every model of GET /models).","contact":{"name":"Doitong","url":"https://doitong.com/developers"}},"servers":[{"url":"https://api.doitong.com/v1","description":"Doitong API"}],"security":[{"bearerAuth":[]}],"tags":[{"name":"Models","description":"The model catalog."},{"name":"Run","description":"Quote and run models."},{"name":"Requests","description":"Status, results and cancellation of runs."},{"name":"Files","description":"Upload input files."},{"name":"Account","description":"API balance (API credits), key limits and file storage."},{"name":"MCP","description":"Model Context Protocol endpoint for AI agents."}],"paths":{"/models":{"get":{"operationId":"listModels","tags":["Models"],"summary":"List models","security":[],"parameters":[{"name":"q","in":"query","required":false,"description":"Words that must all appear in the id, name, maker or tags.","schema":{"type":"string"}},{"name":"category","in":"query","required":false,"description":"Category id.","schema":{"type":"string","enum":["text-to-image","image-to-image","text-to-video","image-to-video","reference-to-video","video-to-video","lipsync","upscale","background-removal","text-to-speech","speech-to-text","text-to-music","audio","video-to-audio","image-to-3d","text-to-3d","3d","training","llm","vision","other"]}},{"name":"lab","in":"query","required":false,"description":"Model maker, by name or slug (any case).","schema":{"type":"string"}},{"name":"family","in":"query","required":false,"description":"Variants group id (the family field of a model).","schema":{"type":"string"}},{"name":"mode","in":"query","required":false,"description":"Price mode.","schema":{"type":"string","enum":["exact","measured","estimate","metered"]}},{"$ref":"#/components/parameters/Limit"},{"name":"cursor","in":"query","required":false,"description":"next_cursor of the previous page.","schema":{"type":"string"}},{"$ref":"#/components/parameters/Currency"}],"responses":{"200":{"description":"A page of models.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ModelList"}}}},"400":{"$ref":"#/components/responses/Error"}}}},"/models/{model_id}":{"get":{"operationId":"getModel","tags":["Models"],"summary":"Get a model","security":[],"parameters":[{"$ref":"#/components/parameters/ModelId"},{"$ref":"#/components/parameters/Currency"}],"responses":{"200":{"description":"The model.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ModelDetail"}}}},"404":{"$ref":"#/components/responses/Error"}}}},"/categories":{"get":{"operationId":"listCategories","tags":["Models"],"summary":"List categories","security":[],"responses":{"200":{"description":"Categories that have models.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/CategoryList"}}}}}}},"/quote/{model_id}":{"post":{"operationId":"quoteModel","tags":["Run"],"summary":"Quote a run of any model","description":"Same body as run; returns the exact API credits and USD. A key is optional; with one the answer also says whether the API balance and the key can pay.","security":[{},{"bearerAuth":[]}],"parameters":[{"$ref":"#/components/parameters/ModelId"},{"$ref":"#/components/parameters/Currency"}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ModelInput"}}}},"responses":{"200":{"description":"The exact price.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Quote"}}}},"404":{"$ref":"#/components/responses/Error"},"422":{"$ref":"#/components/responses/Error"}}}},"/run/{model_id}":{"post":{"operationId":"runModel","tags":["Run"],"summary":"Run any model","parameters":[{"$ref":"#/components/parameters/ModelId"},{"$ref":"#/components/parameters/Wait"},{"name":"webhook_url","in":"query","required":false,"description":"https URL that receives a signed POST when the request finishes.","schema":{"type":"string","format":"uri"}},{"name":"storage","in":"query","required":false,"description":"Where the output files go: permanent (kept until deleted, paid per GB-month) or temporary (free, deleted after 7 days). Default: the account setting (GET /account → storage.mode).","schema":{"$ref":"#/components/schemas/StorageMode"}},{"name":"Idempotency-Key","in":"header","required":false,"description":"Same key + same body returns the same request instead of a second charge.","schema":{"type":"string","maxLength":255}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ModelInput"}}}},"responses":{"200":{"description":"Finished within wait, or an idempotent replay.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Request"}}}},"202":{"description":"Accepted; poll GET /requests/{id}.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Request"}}}},"402":{"$ref":"#/components/responses/Error"},"409":{"$ref":"#/components/responses/Error"},"422":{"$ref":"#/components/responses/Error"},"429":{"$ref":"#/components/responses/Error"},"502":{"$ref":"#/components/responses/Error"},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/requests":{"get":{"operationId":"listRequests","tags":["Requests"],"summary":"List this account's requests","parameters":[{"$ref":"#/components/parameters/Limit"},{"name":"status","in":"query","required":false,"description":"Only this status.","schema":{"$ref":"#/components/schemas/RequestStatus"}},{"name":"model","in":"query","required":false,"description":"Only this model id.","schema":{"type":"string"}},{"name":"cursor","in":"query","required":false,"description":"next_cursor of the previous page.","schema":{"type":"string"}}],"responses":{"200":{"description":"Newest first.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/RequestList"}}}},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/requests/{request_id}":{"get":{"operationId":"getRequest","tags":["Requests"],"summary":"Get a request","parameters":[{"$ref":"#/components/parameters/RequestId"},{"$ref":"#/components/parameters/Wait"},{"name":"logs","in":"query","required":false,"description":"Set to 1 to include the latest log lines.","schema":{"type":"string","enum":["0","1"]}}],"responses":{"200":{"description":"The request.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Request"}}}},"404":{"$ref":"#/components/responses/Error"},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/requests/{request_id}/cancel":{"post":{"operationId":"cancelRequest","tags":["Requests"],"summary":"Cancel a request","parameters":[{"$ref":"#/components/parameters/RequestId"}],"responses":{"200":{"description":"Canceled (refunded), or already canceled.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/CancelResult"}}}},"202":{"description":"The model is already working; cancellation was requested.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/CancelResult"}}}},"404":{"$ref":"#/components/responses/Error"},"409":{"$ref":"#/components/responses/Error"},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/requests/{request_id}/files":{"delete":{"operationId":"deleteRequestFiles","tags":["Requests"],"summary":"Delete a request's output files","description":"Deletes our copies of the output files now and stops their storage charge. The request keeps its URLs with storage.expired = true. Idempotent; a request still running is a 409.","parameters":[{"$ref":"#/components/parameters/RequestId"}],"responses":{"200":{"description":"The request, files deleted.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Request"}}}},"404":{"$ref":"#/components/responses/Error"},"409":{"$ref":"#/components/responses/Error"},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/files":{"post":{"operationId":"createUpload","tags":["Files"],"summary":"Create an upload URL","requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/UploadRequest"}}}},"responses":{"201":{"description":"Upload with PUT, then pass file_url as a model input.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Upload"}}}},"422":{"$ref":"#/components/responses/Error"},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/account":{"get":{"operationId":"getAccount","tags":["Account"],"summary":"API balance and key limits","parameters":[{"$ref":"#/components/parameters/Currency"}],"responses":{"200":{"description":"The account.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Account"}}}},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/account/storage":{"patch":{"operationId":"updateStorageSettings","tags":["Account"],"summary":"Set the default file storage","description":"permanent (default): output files are kept until you delete them, 100 API credits per GB per month from the API balance. temporary: free, deleted after 7 days. Applies to new requests; ?storage= on a run overrides it.","parameters":[{"$ref":"#/components/parameters/Currency"}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/StorageSettingsUpdate"}}}},"responses":{"200":{"description":"The storage settings.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/StorageSettings"}}}},"400":{"$ref":"#/components/responses/Error"},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/mcp":{"post":{"operationId":"mcp","tags":["MCP"],"summary":"MCP endpoint (JSON-RPC 2.0, Streamable HTTP)","description":"Tools: search_models, get_model, quote, run, get_request, cancel_request, list_requests, create_upload, get_account.","requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/JsonRpcRequest"}}}},"responses":{"200":{"description":"JSON-RPC response.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/JsonRpcResponse"}}}},"202":{"description":"Notification accepted (no body)."},"401":{"description":"No API key.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/JsonRpcResponse"}}}}}}},"/run/gemini-tts":{"post":{"operationId":"runGeminiTts","tags":["Run"],"summary":"Run Gemini TTS","description":"Text-to-speech with 30 voices, multi-speaker dialogue, style instructions and a Flash or Pro model choice Price: $0.03 / run.","parameters":[{"$ref":"#/components/parameters/Wait"},{"name":"webhook_url","in":"query","required":false,"description":"https URL that receives a signed POST when the request finishes.","schema":{"type":"string","format":"uri"}},{"name":"storage","in":"query","required":false,"description":"Where the output files go: permanent (kept until deleted, paid per GB-month) or temporary (free, deleted after 7 days). Default: the account setting (GET /account → storage.mode).","schema":{"$ref":"#/components/schemas/StorageMode"}},{"name":"Idempotency-Key","in":"header","required":false,"description":"Same key + same body returns the same request instead of a second charge.","schema":{"type":"string","maxLength":255}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/GeminiTtsInput"}}}},"responses":{"200":{"description":"Finished within wait, or an idempotent replay.","content":{"application/json":{"schema":{"allOf":[{"$ref":"#/components/schemas/Request"},{"type":"object","properties":{"output":{"anyOf":[{"$ref":"#/components/schemas/GeminiTtsOutput"},{"type":"null"}]}}}]}}}},"202":{"description":"Accepted; poll GET /requests/{id}.","content":{"application/json":{"schema":{"allOf":[{"$ref":"#/components/schemas/Request"},{"type":"object","properties":{"output":{"anyOf":[{"$ref":"#/components/schemas/GeminiTtsOutput"},{"type":"null"}]}}}]}}}},"402":{"$ref":"#/components/responses/Error"},"409":{"$ref":"#/components/responses/Error"},"422":{"$ref":"#/components/responses/Error"},"429":{"$ref":"#/components/responses/Error"},"502":{"$ref":"#/components/responses/Error"},"401":{"$ref":"#/components/responses/Error"},"403":{"$ref":"#/components/responses/Error"}}}},"/quote/gemini-tts":{"post":{"operationId":"quoteGeminiTts","tags":["Run"],"summary":"Quote Gemini TTS","description":"Price: $0.03 / run.","security":[{},{"bearerAuth":[]}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/GeminiTtsInput"}}}},"responses":{"200":{"description":"The exact price.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Quote"}}}},"404":{"$ref":"#/components/responses/Error"},"422":{"$ref":"#/components/responses/Error"}}}}},"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","description":"API key (doitong_…) as \"Authorization: Bearer <key>\". \"X-API-Key: <key>\" also works."}},"parameters":{"ModelId":{"name":"model_id","in":"path","required":true,"description":"Model id; may contain slashes (e.g. flux/schnell), written as is.","schema":{"type":"string"}},"RequestId":{"name":"request_id","in":"path","required":true,"schema":{"type":"string","pattern":"^req_[a-z0-9]+$"}},"Limit":{"name":"limit","in":"query","required":false,"schema":{"type":"integer","minimum":1,"maximum":100}},"Currency":{"name":"currency","in":"query","required":false,"description":"rub adds rouble amounts (rate × 1.3) next to USD; usd leaves them out. Default: rub on api.doitong.ru and doitong.ru, usd elsewhere.","schema":{"type":"string","enum":["usd","rub"]}},"Wait":{"name":"wait","in":"query","required":false,"description":"Hold the call up to this many seconds (max 20) and return the finished request if it completes in time.","schema":{"type":"number","minimum":0,"maximum":20}}},"responses":{"Error":{"description":"Error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"schemas":{"ModelInput":{"type":"object","additionalProperties":true,"description":"The model's parameters. See GET /models/{model_id} for its input_schema."},"Error":{"type":"object","required":["error"],"properties":{"error":{"type":"object","required":["type","code","message"],"properties":{"type":{"type":"string","enum":["invalid_request","authentication_error","permission_error","not_found","insufficient_credits","budget_exceeded","conflict","rate_limited","upstream_error","service_unavailable","internal_error"]},"code":{"type":"string"},"message":{"type":"string"},"param":{"type":["string","null"]},"details":{"type":"array","items":{"type":"object","properties":{"param":{"type":"string"},"message":{"type":"string"}}}},"request_id":{"type":["string","null"]},"doc_url":{"type":"string","format":"uri"}}}}},"Price":{"type":"object","description":"Unit price. 1000 API credits = 1 USD (the upstream price).","properties":{"credits":{"type":["number","null"],"description":"API credits per unit (exact prices may have decimals)."},"usd":{"type":["string","null"],"description":"USD per unit, e.g. \"0.112\"."},"rub":{"type":"string","description":"RUB per unit, only with currency=rub or on the RU hosts."},"unit":{"type":"string"},"from_credits":{"type":["integer","null"],"description":"Cheapest plausible single run, in API credits. For a metered model (charged by usage): the typical run, never above hold_credits; a run can settle lower."},"from_usd":{"type":["string","null"]},"from_rub":{"type":"string"},"display":{"type":["string","null"],"description":"e.g. \"$0.112 / second\"."},"credits_display":{"type":["string","null"],"description":"e.g. \"112 API credits / second\"."},"rub_display":{"type":"string","description":"e.g. \"≈ 14.56 ₽ / секунду\" (RU only)."},"mode":{"type":["string","null"],"enum":["exact","measured","estimate","metered",null],"description":"exact: the price is computed from the input; measured: from the length / size of the input files, read before the run; estimate: a flat price per run. All are what a run charges (POST /quote returns the exact amount). metered: charged by actual usage (tokens, seconds of generated speech, processing time) at this unit price — a run holds hold_credits at most and the rest is refunded after it."},"hold_credits":{"type":"integer","description":"metered only: the most a run with the default input can cost (POST /quote gives it for your input)."},"hold_usd":{"type":"string"},"typical_credits":{"type":"integer","description":"metered only: a typical run."},"typical_usd":{"type":"string"},"per":{"type":"string","description":"measured only: what the unit is counted on, e.g. input_video, input_audio, output_video, output_image."},"label":{"type":"string","description":"measured: e.g. \"Price per second of your input video\"; metered: \"Charged by usage\"."}}},"Model":{"type":"object","required":["id","name","category"],"properties":{"id":{"type":"string"},"name":{"type":"string"},"lab":{"type":"string"},"category":{"type":"string"},"summary":{"type":"string"},"tags":{"type":"array","items":{"type":"string"}},"output_kind":{"type":"string"},"thumbnail_url":{"type":["string","null"]},"price":{"$ref":"#/components/schemas/Price"},"docs_url":{"type":"string","format":"uri"},"family":{"type":["string","null"],"description":"Variants group (GET /models?family=)."}}},"ModelDetail":{"allOf":[{"$ref":"#/components/schemas/Model"},{"type":"object","properties":{"description":{"type":"string"},"family":{"type":["string","null"]},"input_schema":{"type":"object"},"output_schema":{"type":"object"},"required_params":{"type":"array","items":{"type":"string"}},"aliases":{"type":"object","additionalProperties":{"type":"string"}},"pricing":{"type":"object"},"example_input":{"type":"object"},"family_ids":{"type":"array","items":{"type":"string"}},"markdown_url":{"type":"string","format":"uri"}}}]},"ModelList":{"type":"object","required":["object","data"],"properties":{"object":{"const":"list"},"data":{"type":"array","items":{"$ref":"#/components/schemas/Model"}},"has_more":{"type":"boolean"},"next_cursor":{"type":["string","null"]}}},"Category":{"type":"object","properties":{"id":{"type":"string"},"name":{"type":"string"},"count":{"type":"integer"}}},"CategoryList":{"type":"object","required":["object","data"],"properties":{"object":{"const":"list"},"data":{"type":"array","items":{"$ref":"#/components/schemas/Category"}}}},"Quote":{"type":"object","required":["object","model","credits"],"properties":{"object":{"const":"quote"},"model":{"type":"string"},"credits":{"type":"integer","description":"API credits this run charges (1000 = 1 USD)."},"usd":{"type":"string","description":"The same amount in USD, e.g. \"0.56\"."},"rub":{"type":"string","description":"In roubles (rate × 1.3), only with currency=rub or on the RU hosts."},"unit":{"type":"string"},"quantity":{"type":"number"},"unit_credits":{"type":"number"},"mode":{"enum":["exact","measured","estimate","metered"],"description":"exact: priced from the input. measured: priced from the length / size of the input files, which were measured for this quote (see measurements; a run with the same files within an hour charges this). estimate: a flat price per run from the typical cost of this model. All are exactly what the run charges. metered: credits is the HOLD — the most this run can cost, debited when it starts; after the run it is settled to the actual usage and the rest is refunded automatically (see hold, typical, and the request's cost.settled)."},"hold":{"type":"object","description":"metered only: { credits, usd (, rub) } — the most the run can cost."},"typical":{"type":["object","null"],"description":"metered only: { credits, usd (, rub) } of a typical run."},"settlement":{"const":"usage","description":"metered only: the run is charged its actual usage."},"label":{"type":"string","description":"\"Price per run\", \"Estimated price per run\" or, measured, e.g. \"Price per second of your input video\"."},"measurements":{"type":"object","description":"measured only: per input param what was measured ({ seconds, width, height, fps, frames, kind })."},"display":{"type":["string","null"]},"breakdown":{"type":["string","null"]},"input":{"type":"object","description":"The normalized input that was priced."},"warnings":{"type":"array","items":{"type":"string"}},"balance_credits":{"type":"integer","description":"API balance in API credits. Only with an API key."},"balance_usd":{"type":"string","description":"Only with an API key."},"affordable":{"type":"boolean","description":"Only with an API key."},"key_budget_remaining":{"type":["integer","null"],"description":"Only with an API key; API credits; null when the key has no cap."},"top_up_url":{"type":"string","format":"uri","description":"Present when the API balance is too low."}}},"RequestStatus":{"type":"string","enum":["queued","running","succeeded","failed","canceled"]},"Output":{"type":"object","required":["type","url"],"properties":{"type":{"type":"string","enum":["image","video","audio","file","3d"]},"url":{"type":"string","format":"uri"},"content_type":{"type":["string","null"]},"file_size":{"type":["integer","null"]},"width":{"type":["integer","null"]},"height":{"type":["integer","null"]},"duration":{"type":["number","null"]},"stored":{"type":"boolean"},"expired":{"type":"boolean","description":"Present (true) once our copy was deleted; the URL no longer works."}}},"StorageMode":{"type":"string","enum":["permanent","temporary"]},"StorageSettingsUpdate":{"type":"object","required":["mode"],"additionalProperties":false,"properties":{"mode":{"$ref":"#/components/schemas/StorageMode"}}},"RequestStorage":{"type":"object","description":"Where the output files are kept (DESIGN.md §17).","properties":{"mode":{"$ref":"#/components/schemas/StorageMode"},"bytes":{"type":"integer","description":"Bytes of our copies of the output files."},"expires_at":{"type":["string","null"],"format":"date-time","description":"When the files are deleted (temporary); null when kept until you delete them."},"expired":{"type":"boolean","description":"true once the files were deleted."}}},"StorageSettings":{"type":"object","properties":{"object":{"type":"string","description":"\"storage_settings\" from PATCH /account/storage."},"mode":{"$ref":"#/components/schemas/StorageMode"},"price_credits_per_gb_month":{"type":"integer","description":"API credits per GB (1024^3 bytes) per month of permanent storage."},"price_usd_per_gb_month":{"type":"string"},"price_rub_per_gb_month":{"type":"string","description":"Only with currency=rub or on the RU hosts."},"temporary_retention_days":{"type":"integer"},"used_bytes":{"type":"integer","description":"Bytes kept permanently (billed)."},"used_gb":{"type":"string"},"expiring_bytes":{"type":"integer","description":"Bytes waiting to be deleted."},"monthly_estimate_credits":{"type":"integer"},"monthly_estimate_usd":{"type":"string"},"grace_started_at":{"type":["string","null"],"format":"date-time","description":"The API balance stopped covering storage at this time."},"grace_until":{"type":["string","null"],"format":"date-time","description":"Top up before this time, or the permanent files become temporary."}}},"Request":{"type":"object","required":["id","object","model","status"],"properties":{"id":{"type":"string"},"object":{"const":"request"},"model":{"type":"string"},"status":{"$ref":"#/components/schemas/RequestStatus"},"created_at":{"type":"string","format":"date-time"},"started_at":{"type":["string","null"],"format":"date-time"},"completed_at":{"type":["string","null"],"format":"date-time"},"queue_position":{"type":["integer","null"]},"cost":{"type":"object","description":"API credits (1000 = 1 USD).","properties":{"credits":{"type":"integer","description":"The quoted price (metered: the hold)."},"usd":{"type":"string","description":"The quoted price in USD."},"charged":{"type":"integer","description":"Debited from the API balance."},"refunded":{"type":"integer","description":"Given back (failure, cancel, or the unused part of a metered hold)."},"mode":{"const":"metered","description":"Only on metered requests."},"held":{"type":"integer","description":"metered only: the hold debited at the start."},"typical":{"type":"integer","description":"metered only: a typical run, API credits."},"settled":{"type":["object","null"],"description":"metered only, once the request succeeded: status settled (credits = what the usage cost = charged − refunded), pending, or no_usage (the model reported no usage: the hold stands).","properties":{"status":{"enum":["settled","pending","no_usage"]},"credits":{"type":"integer"},"usd":{"type":"string"},"quantity":{"type":"number","description":"Usage units billed."},"unit":{"type":"string","description":"e.g. 1000_tokens, audio_second, compute_second."},"unit_usd":{"type":"string"},"source":{"enum":["billed_usage","processing_time"]},"approximate":{"type":"boolean","description":"true when measured from the processing time."}}}}},"input":{"type":"object"},"output":{"type":["object","null"]},"outputs":{"type":"array","items":{"$ref":"#/components/schemas/Output"}},"error":{"anyOf":[{"type":"object","properties":{"type":{"type":"string"},"code":{"type":"string"},"message":{"type":"string"}}},{"type":"null"}]},"metrics":{"type":["object","null"]},"storage":{"$ref":"#/components/schemas/RequestStorage"},"logs":{"type":"array","items":{"type":"object"}},"urls":{"type":"object","properties":{"self":{"type":"string","format":"uri"},"cancel":{"type":"string","format":"uri"}}}}},"RequestList":{"type":"object","required":["object","data"],"properties":{"object":{"const":"list"},"data":{"type":"array","items":{"$ref":"#/components/schemas/Request"}},"has_more":{"type":"boolean"},"next_cursor":{"type":["string","null"]}}},"CancelResult":{"allOf":[{"$ref":"#/components/schemas/Request"},{"type":"object","properties":{"cancel_requested":{"type":"boolean"}}}]},"UploadRequest":{"type":"object","required":["filename"],"properties":{"filename":{"type":"string","description":"The extension decides the type (jpg, png, webp, mp4, mov, webm)."},"content_type":{"type":"string"},"size":{"type":"integer","minimum":1,"description":"Bytes."}}},"Upload":{"type":"object","properties":{"object":{"const":"upload"},"upload_url":{"type":"string","format":"uri"},"file_url":{"type":"string","format":"uri"},"method":{"const":"PUT"},"headers":{"type":"object","additionalProperties":{"type":"string"}},"content_type":{"type":"string"},"expires_in":{"type":"integer"},"max_bytes":{"type":"integer"}}},"Account":{"type":"object","properties":{"object":{"const":"account"},"credits":{"type":"integer","description":"API balance in API credits (1000 = 1 USD). Separate from the Doitong app credits."},"balance":{"type":"object","properties":{"credits":{"type":"integer"},"usd":{"type":"string"},"rub":{"type":"string","description":"Only with currency=rub or on the RU hosts."}}},"top_up_url":{"type":"string","format":"uri"},"key":{"type":"object","properties":{"name":{"type":"string"},"prefix":{"type":"string"},"scopes":{"type":"array","items":{"type":"string"}},"budget_remaining":{"type":["integer","null"],"description":"API credits; null: no cap on the key, the API balance is the limit."},"rate_limit":{"type":"integer"},"rate_limit_remaining":{"type":"integer"}}},"webhook_signing_secret":{"type":"string","description":"HMAC-SHA256 secret of the Doitong-Signature header."},"storage":{"$ref":"#/components/schemas/StorageSettings"}}},"JsonRpcRequest":{"type":"object","required":["jsonrpc","method"],"properties":{"jsonrpc":{"const":"2.0"},"id":{"type":["string","integer","null"]},"method":{"type":"string"},"params":{"type":"object"}}},"JsonRpcResponse":{"type":"object","required":["jsonrpc"],"properties":{"jsonrpc":{"const":"2.0"},"id":{"type":["string","integer","null"]},"result":{"type":"object"},"error":{"type":"object"}}},"GeminiTtsInput":{"description":"Input for Gemini text-to-speech generation.","properties":{"language_code":{"anyOf":[{"enum":["Arabic (Egypt)","Bangla (Bangladesh)","Dutch (Netherlands)","English (India)","English (US)","French (France)","German (Germany)","Hindi (India)","Indonesian (Indonesia)","Italian (Italy)","Japanese (Japan)","Korean (South Korea)","Marathi (India)","Polish (Poland)","Portuguese (Brazil)","Romanian (Romania)","Russian (Russia)","Spanish (Spain)","Tamil (India)","Telugu (India)","Thai (Thailand)","Turkish (Turkey)","Ukrainian (Ukraine)","Vietnamese (Vietnam)","Afrikaans (South Africa)","Albanian (Albania)","Amharic (Ethiopia)","Arabic (World)","Armenian (Armenia)","Azerbaijani (Azerbaijan)","Basque (Spain)","Belarusian (Belarus)","Bulgarian (Bulgaria)","Burmese (Myanmar)","Catalan (Spain)","Cebuano (Philippines)","Chinese Mandarin (China)","Chinese Mandarin (Taiwan)","Croatian (Croatia)","Czech (Czech Republic)","Danish (Denmark)","English (Australia)","English (UK)","Estonian (Estonia)","Filipino (Philippines)","Finnish (Finland)","French (Canada)","Galician (Spain)","Georgian (Georgia)","Greek (Greece)","Gujarati (India)","Haitian Creole (Haiti)","Hebrew (Israel)","Hungarian (Hungary)","Icelandic (Iceland)","Javanese (Java)","Kannada (India)","Konkani (India)","Lao (Laos)","Latin (Vatican City)","Latvian (Latvia)","Lithuanian (Lithuania)","Luxembourgish (Luxembourg)","Macedonian (North Macedonia)","Maithili (India)","Malagasy (Madagascar)","Malay (Malaysia)","Malayalam (India)","Mongolian (Mongolia)","Nepali (Nepal)","Norwegian Bokmal (Norway)","Norwegian Nynorsk (Norway)","Odia (India)","Pashto (Afghanistan)","Persian (Iran)","Portuguese (Portugal)","Punjabi (India)","Serbian (Serbia)","Sindhi (India)","Sinhala (Sri Lanka)","Slovak (Slovakia)","Slovenian (Slovenia)","Spanish (Latin America)","Spanish (Mexico)","Swahili (Kenya)","Swedish (Sweden)","Urdu (Pakistan)"],"type":"string"},{"type":"null"}],"description":"Speech language for multilingual synthesis: omit it to let the model infer the language from your text, or supply it to guide the spoken output. Coverage includes 60+ languages in Preview and 24 in GA.","examples":["English (US)","French (France)","Japanese (Japan)"],"title":"Language Code"},"model":{"default":"gemini-2.5-flash-tts","description":"Gemini TTS model selection. For the highest quality in structured workflows such as audiobooks, podcasts, or customer support, use gemini-2.5-pro-tts.","enum":["gemini-2.5-flash-tts","gemini-2.5-pro-tts"],"title":"Model","type":"string"},"output_format":{"default":"mp3","description":"Format for the output audio: mp3 provides compressed, compact files and is recommended; wav contains uncompressed PCM in a WAV container at 24 kHz with 16-bit mono audio; ogg_opus uses Opus inside Ogg for a favorable balance of quality and size.","enum":["wav","mp3","ogg_opus"],"title":"Output Format","type":"string"},"prompt":{"description":"Speech text for Gemini TTS, accepting embedded natural-language directions for style, pace, accent, and emotion, such as 'Say cheerfully: Have a wonderful day!'. Inline markers including [slowly], [whispering], [excited], and [extremely fast] also control pace and style. Multiple speakers require lines beginning with aliases from the speakers field, for example 'Alice: Hello!\\nBob: Hi!'.","examples":["Host: Welcome back to AI Frontiers, the podcast where we explore the latest breakthroughs in artificial intelligence. Today we have a very special guest. Doctor Chen, thank you for joining us!\nDrChen: Thanks for having me! I'm excited to be here.\nHost: So, let's dive right in. Your recent paper on neural architecture search has been making waves. Can you tell our listeners what inspired this research?\nDrChen: Absolutely. It all started when we noticed that most existing approaches were optimizing for the wrong metrics. We asked ourselves, what if we could let the model design itself?"],"maxLength":50000,"minLength":1,"title":"Prompt","type":"string"},"speakers":{"anyOf":[{"items":{"description":"Voice configuration for a single speaker in multi-speaker synthesis.","properties":{"speaker_id":{"description":"Speaker alias containing only alphanumeric characters and no whitespace. Identify the speaker by prefixing their prompt text with this alias, as in 'Alice: Hello! Bob: Hi there!'.","examples":["Speaker1","Alice","Narrator"],"pattern":"^\\w+$","title":"Speaker Id","type":"string"},"voice":{"description":"Preset voice assigned to this speaker.","enum":["Achernar","Achird","Algenib","Algieba","Alnilam","Aoede","Autonoe","Callirrhoe","Charon","Despina","Enceladus","Erinome","Fenrir","Gacrux","Iapetus","Kore","Laomedeia","Leda","Orus","Pulcherrima","Puck","Rasalgethi","Sadachbia","Sadaltager","Schedar","Sulafat","Umbriel","Vindemiatrix","Zephyr","Zubenelgenubi"],"title":"Voice","type":"string"}},"required":["voice","speaker_id"],"title":"SpeakerConfig","type":"object","x-doitong-order":["voice","speaker_id"]},"maxItems":10,"minItems":2,"type":"array"},{"type":"null"}],"description":"Speaker configuration supported by gemini-2.5-pro-tts and gemini-2.5-flash-tts, but not gemini-2.5-flash-lite-preview-tts. Providing it enables different voices to read different portions of the text; for each speaker, supply a voice plus a speaker_id alias corresponding to that speaker's prompt prefixes.","examples":[[{"speaker_id":"Host","voice":"Charon"},{"speaker_id":"DrChen","voice":"Kore"}]],"title":"Speakers"},"style_instructions":{"anyOf":[{"maxLength":4000,"type":"string"},{"type":"null"}],"description":"Optional natural-language directions kept separate from spoken content and inserted before the prompt to shape expressiveness, accent, pace, tone, and emotion. Examples include 'Speak warmly and slowly', 'Read this as a dramatic newscast', 'Use a British accent with a cheerful tone', and 'Whisper mysteriously'.","examples":["Say the following in a warm, conversational tone","Read this as a dramatic newscast with gravitas","Speak with a British accent, cheerfully and energetically","This is a podcast conversation. The host is enthusiastic and curious, the guest is knowledgeable and articulate"],"title":"Style Instructions"},"temperature":{"default":1,"description":"Speech randomness setting, ranging in effect from focused, predictable delivery at lower settings to creative, varied delivery at higher settings.","maximum":2,"minimum":0,"title":"Temperature","type":"number"},"voice":{"default":"Kore","description":"Single-speaker voice selection from 30 distinct presets; setting speakers makes this selection inactive. Popular female options are Kore, with a strong and firm delivery, Zephyr, with a bright and clear delivery, and Aoede, with a warm and melodic delivery; popular male options are Puck, upbeat and lively, and Charon, calm and professional.","enum":["Achernar","Achird","Algenib","Algieba","Alnilam","Aoede","Autonoe","Callirrhoe","Charon","Despina","Enceladus","Erinome","Fenrir","Gacrux","Iapetus","Kore","Laomedeia","Leda","Orus","Pulcherrima","Puck","Rasalgethi","Sadachbia","Sadaltager","Schedar","Sulafat","Umbriel","Vindemiatrix","Zephyr","Zubenelgenubi"],"title":"Voice","type":"string"}},"required":["prompt"],"title":"GeminiTTSInput","type":"object","x-doitong-order":["prompt","style_instructions","voice","model","language_code","speakers","temperature","output_format"]},"GeminiTtsOutput":{"description":"Output for Gemini text-to-speech generation.","properties":{"audio":{"description":"Audio file produced by generation.","properties":{"content_type":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"MIME type identifying the file's content.","examples":["image/png"],"title":"Content Type"},"file_name":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"File name, generated automatically when omitted.","examples":["z9RV14K95DvU.png"],"title":"File Name"},"file_size":{"anyOf":[{"type":"integer"},{"type":"null"}],"description":"File size measured in bytes.","examples":[4404019],"title":"File Size"},"url":{"description":"Download URL for the file.","title":"Url","type":"string"}},"required":["url"],"title":"File","type":"object","x-doitong-order":["url","content_type","file_name","file_size"]}},"required":["audio"],"title":"GeminiTTSOutput","type":"object","x-doitong-order":["audio"]}}}}