UltraGPT Developers
Resources
ModelsDocumentationStatusApps
TermsPrivacyAcceptable use
Sign in
ResourcesDocumentation
Documentation

Billing

Requests are billed per token from your prepaid credit balance — never your subscription's chat quota. Before a request starts, your available balance must cover its worst case (input plus max_tokens, or 4,096 output tokens when unset); you are charged only for actual usage.

Previous← OrganizationsAll docs on one pageNextRate limits →
API reference
Get started
QuickstartAuthenticationSDKs & toolsAnthropic SDK & Claude Code
Text
Chat completionsResponses APIStreamingTools & JSONReasoningImages & files inWeb searchProvider routingPrompt cachingModel fallbacksPresetsResponse cachingPlugins & variants
Other models
EmbeddingsImage generationSpeech & transcriptionBatch APIRerank, moderation & searchVideo generationRealtime voice
Production
Idempotent retriesApp attributionKey, credits & generationsManagement keys & activityWebhooksPrompt logs, audit & securityBring your own keyOrganizationsBillingRate limitsErrorsModel deprecationsChangelog