YOUR SELECTED SCENARIO
EstimateCalculating...
THE LONG-PROMPT TAX
System prompt sensitivity
Same conversation, different prompt sizes. All values use list prices and the selected per-call or per-minute view.
SIDE BY SIDE
Pipeline comparison (USD / minute)
All costs are USD per minute, based on full call duration, your assumptions, and each model's own rates. Without a published managed tier, rows are explicitly labeled AOAI Global model-price + BYO speech references, not managed tariffs. Edits to the selected model apply to its rows. Missing prices never become zero.
Selected call breakdown
| Component | Quantity | List rate* | List / call |
|---|
*USD per million tokens, except GPT Live in USD/minute.
Price book & editable deployment rates
Blank = unknown, never free. Edits are user-supplied USD rates for this model and hosting mode, kept only in this page's memory. Clearing a verified rate marks it unknown. No Azure API is called at runtime.
Retail meter provenance
Read the estimate, not an invoice
Each call starts with an uncached prompt. On later turns the prompt and prior conversation are reused at your cache-hit percentage. With equally sized turns, prior caller/agent tokens are each replayed (turns - 1) / 2 times. Cache misses use full input rates.
Native mode reuses audio history; text-response mode reuses caller audio and agent text; cascade and reasoning backends reuse text. Only newly generated speech is synthesized. Reasoning tokens are charged as text output, not retained as visible conversation history.
Silence is a usage assumption, not a price discount or billing guarantee. Each side's entered speech seconds is multiplied by (1 - silence % / 100) before computing fresh and replayed audio tokens, STT, and TTS. Text, prompt, reasoning, turn count, GPT Live session minutes, and the full-call per-minute denominator stay unchanged. With the default 90-second speaking allocation, 5% represents 4.5 seconds with both parties silent; avoid counting silence twice when entering measured speech times.
100% caching is an idealized assumption, not guaranteed prefix-cache eligibility. Audio defaults use the public guide's estimates of 10 input and 20 output audio tokens/sec for Azure OpenAI models. Actual tokens, silence billing, tools, storage, telephony, hosting capacity, tax, and network charges can change the result and are excluded.
Model selection is for economic modeling, not a guarantee of South India deployment availability or supported BYOM audio connections. South India Global is the reference for BYOM models and GPT Live. No South India Voice Live managed-tier or BYO speech meters were found, so those use approved Central India references. Azure HD speech output also deliberately uses Central India rates. GPT-6 is explicitly GPT-6 Sol, short-context Standard pricing. GPT Live voice uses the South India Global rate ($3/hour = $0.05/minute); backend model usage is additional and no Azure HD charge is added. GPT Live's delegation frequency and backend context differ in practice; this estimate uses the same turn-based backend assumptions and a session-minute rate.
If a model has no verified managed tier, its economic reference combines AOAI Global model rates with BYO speech rates and is labeled accordingly. It is not a managed Voice Live price or support claim.
Azure Speech pricing / Azure OpenAI pricing / Model tiers & metering / Voice Agent billing