Lexicost
AI voice agents / Vendors

OpenAI

In its own words: “OpenAI is an AI research and deployment company.”

135 facts on file, pages read .

Components. The parts a per-minute cost is made of: speech-to-text, text-to-speech, realtime speech models, language models and phone carriers.

Price

AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1
AI model rate per million tokensgpt-realtime-2.1-mini
Speech-to-text rate
Speech-to-text rate
Speech-to-text rate
Speech-to-text rate
Speech-to-text rate
Voice (text-to-speech) rate
Voice (text-to-speech) rate
Voice (text-to-speech) rate
Voice (text-to-speech) rate
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1
Realtime speech model rategpt-realtime-2.1-mini
Other phone rates
Other phone rates
Other phone rates
Audio tokens per secondRealtime API
Audio tokens per secondRealtime API

Billing rules

Billing rule
Billing rule
Billing ruleRealtime API
Billing rule
Billing rule
Billing rule
Billing rule
Billing rule
Billing rule
Billing rule

Capacity

Other limits
Other limits
Other limits
Other limits
Other limits

Compliance

HIPAA agreement (BAA)
HIPAA agreement (BAA)
HIPAA agreement (BAA)
Where data is processed
Where data is processed
Where data is processed
Where data is processed
Where data is processed
Other compliance statements
Other compliance statements
Other compliance statements
Other compliance statements
Other compliance statements

What changed

  • 2 Nov 2026. Outbound SIP calling became available to all organizations through the Live API source
  • 20 Oct 2026. 12-hour prompt caching added; 12-hour cache writes cost 2.5x the input token price source
  • 10 Sep 2026. GPT-Live-1 became generally available at $0.05 per minute, billed per second, with backend usage charged separately source
  • 26 Aug 2026. Deprecation announced for whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize, with shutdown on February 26, 2027 source
  • 30 Jul 2026. GPT-5.6 Luna price cut by 80% and GPT-5.6 Terra by 20% source
  • 28 Jul 2026. GPT-Transcribe and GPT-Live-Transcribe released source
  • 6 Jul 2026. GPT-Realtime-2.1 and GPT-Realtime-2.1 mini released source
  • 12 May 2026. Realtime API Beta removed from the API source
  • 7 May 2026. GPT-Realtime-2, GPT-Realtime-Translate and GPT-Realtime-Whisper released source

Pages we read

Lexicost has no commercial relationship with any vendor named on this site. Spotted an error? See corrections.

Source for every vendor figure on this page (135)
  1. OpenAI, realtime speech model rate: $32.00 per 1M audio input tokens (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); audio input tokens; Realtime API).gpt-realtime-2.1 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  2. OpenAI, realtime speech model rate: $0.40 per 1M audio cached input tokens (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); audio cached input tokens; Realtime API).gpt-realtime-2.1 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  3. OpenAI, realtime speech model rate: $64.00 per 1M audio output tokens (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); audio output tokens; Realtime API).gpt-realtime-2.1 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  4. OpenAI, aI model rate per million tokens: $4.00 per 1M text input tokens (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); text input tokens; Realtime API).gpt-realtime-2.1 Audio $32.00 $64.00 $0.40 Text $4.00 $24.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  5. OpenAI, aI model rate per million tokens: $0.40 per 1M text cached input tokens (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); text cached input tokens; Realtime API).gpt-realtime-2.1 Audio $32.00 $64.00 $0.40 Text $4.00 $24.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  6. OpenAI, aI model rate per million tokens: $24.00 per 1M text output tokens (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); text output tokens; Realtime API).gpt-realtime-2.1 Audio $32.00 $64.00 $0.40 Text $4.00 $24.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  7. OpenAI, realtime speech model rate: $16.00 per 1M audio input tokens, Batch (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; audio input tokens).Audio: $16.00 / 1M tokens for inputs $0.20 / 1M tokens for cached inputs $32.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  8. OpenAI, realtime speech model rate: $0.20 per 1M audio cached input tokens, Batch (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; audio cached input tokens).Audio: $16.00 / 1M tokens for inputs $0.20 / 1M tokens for cached inputs $32.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  9. OpenAI, realtime speech model rate: $32.00 per 1M audio output tokens, Batch (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; audio output tokens).Audio: $16.00 / 1M tokens for inputs $0.20 / 1M tokens for cached inputs $32.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  10. OpenAI, aI model rate per million tokens: $2.00 per 1M text input tokens, Batch (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; text input tokens).Text: $2.00 / 1M tokens for inputs $0.20 / 1M tokens for cached inputs $12.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  11. OpenAI, aI model rate per million tokens: $0.20 per 1M text cached input tokens, Batch (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; text cached input tokens).Text: $2.00 / 1M tokens for inputs $0.20 / 1M tokens for cached inputs $12.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  12. OpenAI, aI model rate per million tokens: $12.00 per 1M text output tokens, Batch (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; text output tokens).Text: $2.00 / 1M tokens for inputs $0.20 / 1M tokens for cached inputs $12.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  13. OpenAI, realtime speech model rate: $35.20 per 1M audio input tokens, data residency (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; audio input tokens).Audio: $35.20 / 1M tokens for inputs $0.44 / 1M tokens for cached inputs $70.40 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  14. OpenAI, realtime speech model rate: $0.44 per 1M audio cached input tokens, data residency (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; audio cached input tokens).Audio: $35.20 / 1M tokens for inputs $0.44 / 1M tokens for cached inputs $70.40 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  15. OpenAI, realtime speech model rate: $70.40 per 1M audio output tokens, data residency (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; audio output tokens).Audio: $35.20 / 1M tokens for inputs $0.44 / 1M tokens for cached inputs $70.40 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  16. OpenAI, aI model rate per million tokens: $4.40 per 1M text input tokens, data residency (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; text input tokens).Text: $4.40 / 1M tokens for inputs $0.44 / 1M tokens for cached inputs $26.40 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  17. OpenAI, aI model rate per million tokens: $0.44 per 1M text cached input tokens, data residency (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; text cached input tokens).Text: $4.40 / 1M tokens for inputs $0.44 / 1M tokens for cached inputs $26.40 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  18. OpenAI, aI model rate per million tokens: $26.40 per 1M text output tokens, data residency (gpt-realtime-2.1) (gpt-realtime-2.1. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; text output tokens).Text: $4.40 / 1M tokens for inputs $0.44 / 1M tokens for cached inputs $26.40 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  19. OpenAI, realtime speech model rate: $10.00 per 1M audio input tokens (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); audio input tokens; Realtime API).gpt-realtime-2.1-mini Audio $10.00 $20.00 $0.30 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  20. OpenAI, realtime speech model rate: $0.30 per 1M audio cached input tokens (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); audio cached input tokens; Realtime API).gpt-realtime-2.1-mini Audio $10.00 $20.00 $0.30 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  21. OpenAI, realtime speech model rate: $20.00 per 1M audio output tokens (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); audio output tokens; Realtime API).gpt-realtime-2.1-mini Audio $10.00 $20.00 $0.30 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  22. OpenAI, aI model rate per million tokens: $0.60 per 1M text input tokens (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); text input tokens; Realtime API).gpt-realtime-2.1-mini Audio $10.00 $20.00 $0.30 Text $0.60 $2.40 $0.06 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  23. OpenAI, aI model rate per million tokens: $0.06 per 1M text cached input tokens (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); text cached input tokens; Realtime API).gpt-realtime-2.1-mini Audio $10.00 $20.00 $0.30 Text $0.60 $2.40 $0.06 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  24. OpenAI, aI model rate per million tokens: $2.40 per 1M text output tokens (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. Standard processing (not Batch, not data residency; the business pricing page lists those rates as separate facts); text output tokens; Realtime API).gpt-realtime-2.1-mini Audio $10.00 $20.00 $0.30 Text $0.60 $2.40 $0.06 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  25. OpenAI, realtime speech model rate: $5.00 per 1M audio input tokens, Batch (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; audio input tokens).Audio: $5.00 / 1M tokens for inputs $0.15 / 1M tokens for cached inputs $10.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  26. OpenAI, realtime speech model rate: $0.15 per 1M audio cached input tokens, Batch (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; audio cached input tokens).Audio: $5.00 / 1M tokens for inputs $0.15 / 1M tokens for cached inputs $10.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  27. OpenAI, realtime speech model rate: $10.00 per 1M audio output tokens, Batch (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; audio output tokens).Audio: $5.00 / 1M tokens for inputs $0.15 / 1M tokens for cached inputs $10.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  28. OpenAI, aI model rate per million tokens: $0.30 per 1M text input tokens, Batch (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; text input tokens).Text: $0.30 / 1M tokens for inputs $0.03 / 1M tokens for cached inputs $1.20 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  29. OpenAI, aI model rate per million tokens: $0.03 per 1M text cached input tokens, Batch (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; text cached input tokens).Text: $0.30 / 1M tokens for inputs $0.03 / 1M tokens for cached inputs $1.20 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  30. OpenAI, aI model rate per million tokens: $1.20 per 1M text output tokens, Batch (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page; text output tokens).Text: $0.30 / 1M tokens for inputs $0.03 / 1M tokens for cached inputs $1.20 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  31. OpenAI, realtime speech model rate: $11.00 per 1M audio input tokens, data residency (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; audio input tokens).Audio: $11.00 / 1M tokens for inputs $0.33 / 1M tokens for cached inputs $22.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  32. OpenAI, realtime speech model rate: $0.33 per 1M audio cached input tokens, data residency (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; audio cached input tokens).Audio: $11.00 / 1M tokens for inputs $0.33 / 1M tokens for cached inputs $22.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  33. OpenAI, realtime speech model rate: $22.00 per 1M audio output tokens, data residency (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; audio output tokens).Audio: $11.00 / 1M tokens for inputs $0.33 / 1M tokens for cached inputs $22.00 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  34. OpenAI, aI model rate per million tokens: $0.66 per 1M text input tokens, data residency (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; text input tokens).Text: $0.66 / 1M tokens for inputs $0.066 / 1M tokens for cached inputs $2.64 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  35. OpenAI, aI model rate per million tokens: $0.066 per 1M text cached input tokens, data residency (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; text cached input tokens).Text: $0.66 / 1M tokens for inputs $0.066 / 1M tokens for cached inputs $2.64 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  36. OpenAI, aI model rate per million tokens: $2.64 per 1M text output tokens, data residency (gpt-realtime-2.1-mini) (gpt-realtime-2.1-mini. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page; text output tokens).Text: $0.66 / 1M tokens for inputs $0.066 / 1M tokens for cached inputs $2.64 / 1M tokens for outputs openai.com/business/pricing Read 14 Nov 2026.
  37. OpenAI, realtime speech model rate: $32.00 per 1M audio input tokens (gpt-realtime-2) (gpt-realtime-2. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio input tokens; Realtime API).gpt-realtime-2 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  38. OpenAI, realtime speech model rate: $0.40 per 1M audio cached input tokens (gpt-realtime-2) (gpt-realtime-2. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio cached input tokens; Realtime API).gpt-realtime-2 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  39. OpenAI, realtime speech model rate: $64.00 per 1M audio output tokens (gpt-realtime-2) (gpt-realtime-2. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio output tokens; Realtime API).gpt-realtime-2 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  40. OpenAI, aI model rate per million tokens: $4.00 per 1M text input tokens (gpt-realtime-2) (gpt-realtime-2. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text input tokens; Realtime API).gpt-realtime-2 Audio $32.00 $64.00 $0.40 Text $4.00 $24.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  41. OpenAI, aI model rate per million tokens: $0.40 per 1M text cached input tokens (gpt-realtime-2) (gpt-realtime-2. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text cached input tokens; Realtime API).gpt-realtime-2 Audio $32.00 $64.00 $0.40 Text $4.00 $24.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  42. OpenAI, aI model rate per million tokens: $24.00 per 1M text output tokens (gpt-realtime-2) (gpt-realtime-2. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text output tokens; Realtime API).gpt-realtime-2 Audio $32.00 $64.00 $0.40 Text $4.00 $24.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  43. OpenAI, realtime speech model rate: $32.00 per 1M audio input tokens (gpt-realtime-1.5) (gpt-realtime-1.5. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio input tokens; Realtime API).gpt-realtime-1.5 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  44. OpenAI, realtime speech model rate: $0.40 per 1M audio cached input tokens (gpt-realtime-1.5) (gpt-realtime-1.5. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio cached input tokens; Realtime API).gpt-realtime-1.5 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  45. OpenAI, realtime speech model rate: $64.00 per 1M audio output tokens (gpt-realtime-1.5) (gpt-realtime-1.5. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio output tokens; Realtime API).gpt-realtime-1.5 Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  46. OpenAI, aI model rate per million tokens: $4.00 per 1M text input tokens (gpt-realtime-1.5) (gpt-realtime-1.5. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text input tokens; Realtime API).gpt-realtime-1.5 Audio $32.00 $64.00 $0.40 Text $4.00 $16.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  47. OpenAI, aI model rate per million tokens: $0.40 per 1M text cached input tokens (gpt-realtime-1.5) (gpt-realtime-1.5. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text cached input tokens; Realtime API).gpt-realtime-1.5 Audio $32.00 $64.00 $0.40 Text $4.00 $16.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  48. OpenAI, aI model rate per million tokens: $16.00 per 1M text output tokens (gpt-realtime-1.5) (gpt-realtime-1.5. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text output tokens; Realtime API).gpt-realtime-1.5 Audio $32.00 $64.00 $0.40 Text $4.00 $16.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  49. OpenAI, realtime speech model rate: $10.00 per 1M audio input tokens (gpt-realtime-mini) (gpt-realtime-mini. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio input tokens; Realtime API).gpt-realtime-mini Audio $10.00 $20.00 $0.30 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  50. OpenAI, realtime speech model rate: $0.30 per 1M audio cached input tokens (gpt-realtime-mini) (gpt-realtime-mini. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio cached input tokens; Realtime API).gpt-realtime-mini Audio $10.00 $20.00 $0.30 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  51. OpenAI, realtime speech model rate: $20.00 per 1M audio output tokens (gpt-realtime-mini) (gpt-realtime-mini. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio output tokens; Realtime API).gpt-realtime-mini Audio $10.00 $20.00 $0.30 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  52. OpenAI, aI model rate per million tokens: $0.60 per 1M text input tokens (gpt-realtime-mini) (gpt-realtime-mini. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text input tokens; Realtime API).gpt-realtime-mini Audio $10.00 $20.00 $0.30 Text $0.60 $2.40 $0.06 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  53. OpenAI, aI model rate per million tokens: $0.06 per 1M text cached input tokens (gpt-realtime-mini) (gpt-realtime-mini. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text cached input tokens; Realtime API).gpt-realtime-mini Audio $10.00 $20.00 $0.30 Text $0.60 $2.40 $0.06 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  54. OpenAI, aI model rate per million tokens: $2.40 per 1M text output tokens (gpt-realtime-mini) (gpt-realtime-mini. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text output tokens; Realtime API).gpt-realtime-mini Audio $10.00 $20.00 $0.30 Text $0.60 $2.40 $0.06 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  55. OpenAI, realtime speech model rate: $32.00 per 1M audio input tokens (gpt-realtime) (gpt-realtime. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio input tokens; Realtime API).gpt-realtime Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  56. OpenAI, realtime speech model rate: $0.40 per 1M audio cached input tokens (gpt-realtime) (gpt-realtime. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio cached input tokens; Realtime API).gpt-realtime Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  57. OpenAI, realtime speech model rate: $64.00 per 1M audio output tokens (gpt-realtime) (gpt-realtime. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; audio output tokens; Realtime API).gpt-realtime Audio $32.00 $64.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  58. OpenAI, aI model rate per million tokens: $4.00 per 1M text input tokens (gpt-realtime) (gpt-realtime. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text input tokens; Realtime API).gpt-realtime Audio $32.00 $64.00 $0.40 Text $4.00 $16.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  59. OpenAI, aI model rate per million tokens: $0.40 per 1M text cached input tokens (gpt-realtime) (gpt-realtime. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text cached input tokens; Realtime API).gpt-realtime Audio $32.00 $64.00 $0.40 Text $4.00 $16.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  60. OpenAI, aI model rate per million tokens: $16.00 per 1M text output tokens (gpt-realtime) (gpt-realtime. pay as you go. Rate as listed on the developer pricing page, which shows no Batch or data-residency rate for this model; text output tokens; Realtime API).gpt-realtime Audio $32.00 $64.00 $0.40 Text $4.00 $16.00 $0.40 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  61. OpenAI, realtime speech model rate: $0.05 per minute, billed per second (gpt-live-1); backend model and tools billed separately (gpt-live-1. pay as you go. Standard processing (not Batch, not data residency); voice session duration; Live API (/v1/live/sessions)).Voice sessions cost $0.05 per minute, billed per second. Backend model and tool usage is billed separately. developers.openai.com/api/docs/models/gpt-live-1 Read 14 Nov 2026.
  62. OpenAI, realtime speech model rate: $0.055 per minute with data residency (gpt-live-1) (gpt-live-1. pay as you go. "Data residency +10%" processing mode selected for Voice models on the business pricing page).$0.055 per minute / $0.000913 per second openai.com/business/pricing Read 14 Nov 2026.
  63. OpenAI, realtime speech model rate: $0.025 per minute, Batch (gpt-live-1) (gpt-live-1. pay as you go. "Batch -50%" processing mode selected for Voice models on the business pricing page).$0.025 per minute / $0.000415 per second openai.com/business/pricing Read 14 Nov 2026.
  64. OpenAI, billing rule: User audio is counted as 1 token per 100 ms; assistant audio as 1 token per 50 ms (Realtime API) (Realtime API speech-to-speech sessions).Audio tokens in user messages are 1 token per 100 ms of audio, while audio tokens in assistant messages are 1 token per 50ms of audio. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  65. OpenAI, audio tokens per second: 10 tokens per second of caller audio (1 per 100 ms) (Realtime API. "Conversational Realtime API sessions" (Cost optimization page, Realtime API tab, Per-Response costs); user (caller) audio; the sentence names no model).Audio tokens in user messages are 1 token per 100 ms of audio, while audio tokens in assistant messages are 1 token per 50ms of audio. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  66. OpenAI, audio tokens per second: 20 tokens per second of agent audio (1 per 50 ms) (Realtime API. "Conversational Realtime API sessions" (Cost optimization page, Realtime API tab, Per-Response costs); assistant (agent) audio; the sentence names no model).Audio tokens in user messages are 1 token per 100 ms of audio, while audio tokens in assistant messages are 1 token per 50ms of audio. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  67. OpenAI, billing rule: Charged per Response on input and output tokens; no charge for bandwidth or connections (Realtime API) (Realtime API speech-to-speech sessions).Realtime API costs are accrued when a Response is created, and is charged based on the numbers of input and output tokens (except for input transcription costs, see below). There is no cost currently for network bandwidth or connections. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  68. OpenAI, billing rule: The whole conversation is sent as input on every Response, so later turns cost more (Realtime API) (Realtime API. "Conversational Realtime API sessions" (Cost optimization page, Realtime API tab)).The entire conversation is sent to the model for each Response. The output from a turn will be added as Items to the server Conversation and become the input to subsequent turns, thus turns later in the session will be more expensive. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  69. OpenAI, billing rule: With voice activity detection on, empty audio is not counted as input tokens unless the client adds it (Realtime API) (Realtime API with voice activity detection (VAD) turned on).VAD will effectively filter out empty input audio, so empty audio doesn’t count as input tokens unless the client manually adds it as conversation input. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  70. OpenAI, billing rule: Input transcription, if enabled, is billed separately on its own model rate (Realtime API) (Realtime API sessions with input transcription enabled).If enabled, input transcription is billed separately by the Realtime API. Input transcription uses a different model and rate card from the speech-to-speech model. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  71. OpenAI, billing rule: gpt-transcribe input transcription is billed by audio duration; token-priced transcription models report tokens (Realtime API input transcription).The usage fields depend on the transcription model: gpt-transcribe is billed by audio duration, while models billed by token usage return token counts. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  72. OpenAI, billing rule: Streaming translation and streaming transcription sessions are billed by audio duration (Realtime translation and transcription sessions).Streaming translation and streaming transcription sessions are billed by audio duration. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  73. OpenAI, billing rule: Prompt caching is applied automatically to repeated input in multi-turn sessions, best-effort and not guaranteed (Realtime API) (Realtime API speech-to-speech sessions).Realtime API supports prompt caching, which is applied automatically and can dramatically reduce the costs of input tokens during multi-turn sessions. Caching applies when the input tokens of a Response match tokens from a previous Response, though this is best-effort and not guaranteed. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  74. OpenAI, billing rule: Removing or changing earlier content, including instructions and tools, breaks the cache from that point (Realtime API) (Realtime API speech-to-speech sessions).Removing or changing content in the conversation will “bust” the cache up to the point of the change — the input no longer matches as much as before. Note that instructions and tool definitions are at the beginning of a conversation, thus changing these mid-session will reduce the cache rate for subsequent turns. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  75. OpenAI, billing rule: When a conversation exceeds the model's input limit, the oldest messages are dropped from the input (Realtime API) (Realtime API speech-to-speech sessions).When the number of tokens in a conversation exceeds the model’s input token limit the conversation be truncated, meaning messages (starting from the oldest) will be dropped from the Response input. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  76. OpenAI, billing rule: Clients can set a smaller token window than the model maximum to control token use and cost (Realtime API) (Realtime API speech-to-speech sessions).Clients can set a smaller token window than the model’s maximum, which is a good way to control token usage and cost. This is controlled with the token_limits.post_instructions configuration (if you configure truncation with a retention_ratio type as shown below). developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  77. OpenAI, billing rule: Truncation breaks the cache near the start of the conversation; truncating every turn keeps the cache rate low (Realtime API) (Realtime API speech-to-speech sessions).Truncation busts the cache near the beginning of the conversation, and if truncation occurs on every turn then cache rate will be very low. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  78. OpenAI, billing rule: Realtime speech-to-speech models come in a normal size and a cheaper mini size (Realtime API).The Realtime speech2speech models come in a “normal” size and a mini size, which is significantly cheaper. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  79. OpenAI, billing rule: Deleting old messages from the conversation reduces input tokens and cost (Realtime API) (Realtime API).Clearing out old messages is a good way to reduce input token sizes and cost. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  80. OpenAI, billing rule: Realtime token costs are hard to estimate ahead; OpenAI suggests measuring a sample session (Realtime API token-priced models).Given the complexity in Realtime API token usage it can be difficult to estimate your costs ahead of time. A good approach is to use the Realtime Playground with your intended prompts and functions, and measure the token usage over a sample session. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  81. OpenAI, billing rule: GPT-Live sessions are billed per second, with no rounding up to a whole minute (gpt-live-1, Live API).GPT-Live voice sessions are billed per second at the current model rate. Session duration is not rounded up to the next whole minute. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  82. OpenAI, billing rule: GPT-Live billed time includes silence and time the backend is working (gpt-live-1, Live API).Active session time includes time when the user speaks, the assistant speaks, both are silent, or the backend is working. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  83. OpenAI, billing rule: For GPT-Live estimates, count the session from start to close, not only the audio played (gpt-live-1. GPT-Live voice sessions).For estimates, count the active session from start through closure. Use the duration reported by the API instead of timing only the audio you play. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  84. OpenAI, billing rule: GPT-Live cost = billable voice seconds / 60 x rate per minute, plus backend costs (gpt-live-1. a conversation with one voice session).Total cost = (billable voice seconds ÷ 60 × voice rate per minute) + backend costs developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  85. OpenAI, billing rule: Creating a GPT-Live WebRTC session bills 15 seconds up front, credited against the session once it runs (gpt-live-1 sessions created over WebRTC).A POST /v1/live/sessions request to create a WebRTC session bills 15 seconds of voice duration while the session initializes. That amount is credited against duration charges once the session starts running. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  86. OpenAI, billing rule: GPT-Live backend model and tool calls are billed separately from the voice session (gpt-live-1, Live API).Backend calls are billed separately from the voice session, just as they are in applications without voice. developers.openai.com/api/docs/guides/voice-latency-cost Read 14 Nov 2026.
  87. OpenAI, billing rule: A hard spend limit makes affected API requests return a 429 error at the configured monthly amount (organization or project setting).Hard spend limit Affected API requests return a 429 error Enforce a monthly organization or project cap developers.openai.com/api/docs/guides/rate-limits Read 14 Nov 2026.
  88. OpenAI, billing rule: Text models: cache writes are charged at a cache-write rate instead of the input rate, not as an extra fee (text models with prompt caching).Prompt caching pricing varies by model. See API pricing for current cached-input and cache-write rates. Cache-write pricing is not an additive fee: input tokens use the uncached-input, cached-input, or cache-write rate. developers.openai.com/api/docs/guides/prompt-caching Read 14 Nov 2026.
  89. OpenAI, billing rule: GPT-5.6 and later: cache writes cost 1.25x for "30m" and 2.5x for "12h" in the Responses API; cache reads 0.1x uncached input (0.05x for GPT-6.1 Sol and Terra) (GPT-5.6 and later text models, cache writes in the Responses API; earlier models have no additional cache-write charge).Cache read charge 0.1× uncached input (0.05× for GPT-6.1 Sol and GPT-6.1 Terra) Model-dependent cached-input rate Model-dependent cached-input rate Cache write charge 1.25× for "30m"; 2.5× for "12h" in the Responses API No additional cache-write charge No additional cache-write charge developers.openai.com/api/docs/guides/prompt-caching Read 14 Nov 2026.
  90. OpenAI, billing rule: tts-1, tts-1-hd and gpt-4o-mini-tts shut down January 6, 2027; OpenAI points to gpt-realtime-2.1-mini instead (Speech API (/v1/audio/speech)).The tts-1, tts-1-hd, and gpt-4o-mini-tts models are deprecated and will shut down on January 6, 2027. Migrate to gpt-realtime-2.1-mini using the Realtime API. developers.openai.com/api/docs/guides/text-to-speech Read 14 Nov 2026.
  91. OpenAI, aI model rate per million tokens: $1.00 per 1M input tokens (gpt-6.1-terra) (pay as you go, Standard processing. gpt-6.1-terra, text input tokens, default (Short) context-length view).gpt-6.1-terra $1.00 $5.00 $0.05 $1.25 $2.50 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  92. OpenAI, aI model rate per million tokens: $0.05 per 1M cached input tokens (gpt-6.1-terra) (pay as you go, Standard processing. gpt-6.1-terra, text cached input tokens, default (Short) context-length view).gpt-6.1-terra $1.00 $5.00 $0.05 $1.25 $2.50 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  93. OpenAI, aI model rate per million tokens: $5.00 per 1M output tokens (gpt-6.1-terra) (pay as you go, Standard processing. gpt-6.1-terra, text output tokens, default (Short) context-length view).gpt-6.1-terra $1.00 $5.00 $0.05 $1.25 $2.50 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  94. OpenAI, aI model rate per million tokens: $0.10 per 1M input tokens (gpt-6-luna) (pay as you go, Standard processing. gpt-6-luna, text input tokens, default (Short) context-length view).gpt-6-luna $0.10 $0.50 $0.01 $0.125 $0.25 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  95. OpenAI, aI model rate per million tokens: $0.01 per 1M cached input tokens (gpt-6-luna) (pay as you go, Standard processing. gpt-6-luna, text cached input tokens, default (Short) context-length view).gpt-6-luna $0.10 $0.50 $0.01 $0.125 $0.25 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  96. OpenAI, aI model rate per million tokens: $0.50 per 1M output tokens (gpt-6-luna) (pay as you go, Standard processing. gpt-6-luna, text output tokens, default (Short) context-length view).gpt-6-luna $0.10 $0.50 $0.01 $0.125 $0.25 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  97. OpenAI, aI model rate per million tokens: $2.00 per 1M input tokens (gpt-5.6-terra) (pay as you go, Standard processing. gpt-5.6-terra, text input tokens, default (Short) context-length view).gpt-5.6-terra $2.00 $12.00 $0.20 $2.50 $5.00 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  98. OpenAI, aI model rate per million tokens: $0.20 per 1M cached input tokens (gpt-5.6-terra) (pay as you go, Standard processing. gpt-5.6-terra, text cached input tokens, default (Short) context-length view).gpt-5.6-terra $2.00 $12.00 $0.20 $2.50 $5.00 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  99. OpenAI, aI model rate per million tokens: $12.00 per 1M output tokens (gpt-5.6-terra) (pay as you go, Standard processing. gpt-5.6-terra, text output tokens, default (Short) context-length view).gpt-5.6-terra $2.00 $12.00 $0.20 $2.50 $5.00 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  100. OpenAI, aI model rate per million tokens: $0.20 per 1M input tokens (gpt-5.6-luna) (pay as you go, Standard processing. gpt-5.6-luna, text input tokens, default (Short) context-length view).gpt-5.6-luna $0.20 $1.20 $0.02 $0.25 $0.50 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  101. OpenAI, aI model rate per million tokens: $0.02 per 1M cached input tokens (gpt-5.6-luna) (pay as you go, Standard processing. gpt-5.6-luna, text cached input tokens, default (Short) context-length view).gpt-5.6-luna $0.20 $1.20 $0.02 $0.25 $0.50 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  102. OpenAI, aI model rate per million tokens: $1.20 per 1M output tokens (gpt-5.6-luna) (pay as you go, Standard processing. gpt-5.6-luna, text output tokens, default (Short) context-length view).gpt-5.6-luna $0.20 $1.20 $0.02 $0.25 $0.50 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  103. OpenAI, aI model rate per million tokens: $0.75 per 1M input tokens (gpt-5.4-mini) (pay as you go, Standard processing. gpt-5.4-mini, text input tokens, default (Short) context-length view).gpt-5.4-mini $0.75 $4.50 $0.075 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  104. OpenAI, aI model rate per million tokens: $0.075 per 1M cached input tokens (gpt-5.4-mini) (pay as you go, Standard processing. gpt-5.4-mini, text cached input tokens, default (Short) context-length view).gpt-5.4-mini $0.75 $4.50 $0.075 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  105. OpenAI, aI model rate per million tokens: $4.50 per 1M output tokens (gpt-5.4-mini) (pay as you go, Standard processing. gpt-5.4-mini, text output tokens, default (Short) context-length view).gpt-5.4-mini $0.75 $4.50 $0.075 developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  106. OpenAI, speech-to-text rate: $0.017 per minute (gpt-live-transcribe, live transcription) (pay as you go, standard rates. gpt-live-transcribe, live transcription).gpt-live-transcribe Live transcription - - $0.017 / minute developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  107. OpenAI, speech-to-text rate: $0.017 per minute (gpt-realtime-whisper, live transcription) (pay as you go, standard rates. gpt-realtime-whisper, live transcription).gpt-realtime-whisper Live transcription - - $0.017 / minute developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  108. OpenAI, speech-to-text rate: $0.0045 per minute (gpt-transcribe) (pay as you go, standard rates. gpt-transcribe, transcription).gpt-transcribe Transcription - - $0.0045 / minute developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  109. OpenAI, speech-to-text rate: About $0.006 per minute, estimated (gpt-4o-transcribe; billed $2.50 input and $10.00 output per 1M tokens) (pay as you go, standard rates. gpt-4o-transcribe; per-minute figure is OpenAI's estimate, billing is per token).gpt-4o-transcribe Transcription $2.50 $10.00 $0.006 / minute developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  110. OpenAI, speech-to-text rate: About $0.003 per minute, estimated (gpt-4o-mini-transcribe; billed $1.25 input and $5.00 output per 1M tokens) (pay as you go, standard rates. gpt-4o-mini-transcribe; per-minute figure is OpenAI's estimate, billing is per token).gpt-4o-mini-transcribe Transcription $1.25 $5.00 $0.003 / minute developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  111. OpenAI, voice (text-to-speech) rate: $12.00 per 1M audio output tokens (gpt-4o-mini-tts) (pay as you go, standard rates. gpt-4o-mini-tts, audio output tokens).gpt-4o-mini-tts Audio - $12.00 - Text $0.60 - - developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  112. OpenAI, voice (text-to-speech) rate: $0.60 per 1M text input tokens (gpt-4o-mini-tts) (pay as you go, standard rates. gpt-4o-mini-tts, text input tokens).gpt-4o-mini-tts Audio - $12.00 - Text $0.60 - - developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  113. OpenAI, voice (text-to-speech) rate: $15.00 per 1M characters (tts-1) (pay as you go, standard rates. tts-1).tts-1 Text $15.00 / 1M characters - - developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  114. OpenAI, voice (text-to-speech) rate: $30.00 per 1M characters (tts-1-hd) (pay as you go, standard rates. tts-1-hd).tts-1-hd Text $30.00 / 1M characters - - developers.openai.com/api/docs/pricing Read 14 Nov 2026.
  115. OpenAI, other phone rates: To connect a phone number, use a SIP trunking provider such as Twilio (Realtime API) (Realtime API over SIP).If you want to connect a phone number to the Realtime API, use a SIP trunking provider (e.g., Twilio). This is a service that converts your phone call to IP traffic. developers.openai.com/api/docs/guides/voice-sip Read 14 Nov 2026.
  116. OpenAI, other phone rates: Outbound SIP calls are available to all organizations through the Live API, not the Realtime API (GPT-Live over SIP).Outbound SIP calling is available to all organizations through the Live API, not the Realtime API call-creation endpoint. developers.openai.com/api/docs/guides/voice-sip Read 14 Nov 2026.
  117. OpenAI, other phone rates: Not publicly listed (Realtime API and GPT-Live over SIP). Read 14 Nov 2026.
  118. OpenAI, other limits: gpt-live-1 concurrent sessions by usage tier: Free not supported, Build 50, Launch 300, Grow 500 (gpt-live-1, per usage tier).Rate limits are measured in concurrent sessions. TIER CONCURRENT SESSIONS Free Not supported Build 50 Launch 300 Grow 500 developers.openai.com/api/docs/models/gpt-live-1 Read 14 Nov 2026.
  119. OpenAI, other limits: gpt-realtime-2.1 by usage tier: Free not supported; Build 400 RPM and 200,000 TPM; Launch 10,000 RPM and 4,000,000 TPM; Grow 20,000 RPM and 15,000,000 TPM (gpt-realtime-2.1, per usage tier).TIER RPM TPM Free Not supported Build 400 200,000 Launch 10,000 4,000,000 Grow 20,000 15,000,000 developers.openai.com/api/docs/models/gpt-realtime-2.1 Read 14 Nov 2026.
  120. OpenAI, other limits: gpt-realtime-2.1-mini by usage tier: Free not supported; Build 400 RPM and 200,000 TPM; Launch 10,000 RPM and 4,000,000 TPM; Grow 20,000 RPM and 15,000,000 TPM (gpt-realtime-2.1-mini, per usage tier).TIER RPM TPM Free Not supported Build 400 200,000 Launch 10,000 4,000,000 Grow 20,000 15,000,000 developers.openai.com/api/docs/models/gpt-realtime-2.1-mini Read 14 Nov 2026.
  121. OpenAI, other limits: Usage tiers: Free (allowed geography, $100/month), Build ($5 purchased, $500/month), Launch ($100 purchased, $5,000/month), Grow ($500 purchased, $200,000/month) (API organization usage tier).Tier Qualification Usage limits Free User must be in an allowed geography $100 / month Build $5 in total credit purchases $500 / month Launch $100 in total credit purchases $5,000 / month Grow $500 in total credit purchases $200,000 / month developers.openai.com/api/docs/guides/rate-limits Read 14 Nov 2026.
  122. OpenAI, other limits: GPT-Live SIP calls: ringing up to 3 minutes, a connected call up to 2 hours, not configurable (GPT-Live SIP calls created through the Live API).Ringing is limited to 3 minutes, and a connected call is limited to 2 hours. These limits aren’t configurable in the creation request. developers.openai.com/api/docs/guides/voice-sip Read 14 Nov 2026.
  123. OpenAI, where data is processed: Data residency is available to eligible organizations per project, at a 10% uplift for eligible models released on or after March 5, 2026 (projects created with data residency).Eligible organizations can enable data residency when creating a project in the API Platform. Data residency endpoints are charged a 10% uplift for models released on or after March 5, 2026, that are eligible for data residency. developers.openai.com/api/docs/guides/data-residency Read 14 Nov 2026.
  124. OpenAI, where data is processed: GPT-Live supports data residency in the United States and Europe; delegated backend models have their own controls (gpt-live-1, /v1/live/sessions).GPT-Live supports data residency in the United States and Europe. Delegated backend models and tools have their own data controls; check the applicable endpoint and feature entries on this page. developers.openai.com/api/docs/guides/data-residency Read 14 Nov 2026.
  125. OpenAI, where data is processed: Realtime API data residency lists gpt-realtime, gpt-realtime-1.5 and gpt-realtime-mini plus 3 snapshots (/v1/realtime)./v1/realtime Realtime gpt-realtime gpt-realtime-1.5 gpt-realtime-mini + 3 model snapshots — developers.openai.com/api/docs/guides/data-residency Read 14 Nov 2026.
  126. OpenAI, where data is processed: Realtime API tracing is not EU data residency compliant (Europe. /v1/realtime tracing).Tracing is not currently EU data residency compliant for /v1/realtime. developers.openai.com/api/docs/guides/data-residency Read 14 Nov 2026.
  127. OpenAI, where data is processed: SIP has an EU endpoint for European data residency and an India endpoint (Realtime API over SIP).For European data residency, use sip:$PROJECT_ID@sip-eu.api.openai.com;transport=tls. For SIP hosts physically located in India, use sip:$PROJECT_ID@sip-in.api.openai.com;transport=tls. developers.openai.com/api/docs/guides/voice-sip Read 14 Nov 2026.
  128. OpenAI, other compliance statements: API data is not used to train OpenAI models unless you opt in (since March 1, 2023).Your data is your data. As of March 1, 2023, data sent to the OpenAI API is not used to train or improve OpenAI models (unless you explicitly opt in to share data with us). developers.openai.com/api/docs/guides/your-data Read 14 Nov 2026.
  129. OpenAI, other compliance statements: Abuse monitoring logs are kept up to 30 days by default.By default, abuse monitoring logs are generated for all API feature usage and retained for up to 30 days, unless longer retention is required by law, or is reasonably necessary to protect our services or any third party from harm. developers.openai.com/api/docs/guides/your-data Read 14 Nov 2026.
  130. OpenAI, other compliance statements: Zero Data Retention and Modified Abuse Monitoring need prior approval from OpenAI.Currently, these controls are subject to prior approval by OpenAI and acceptance of additional requirements. developers.openai.com/api/docs/guides/your-data Read 14 Nov 2026.
  131. OpenAI, other compliance statements: /v1/realtime: not used for training, 30-day abuse monitoring retention, eligible for Zero Data Retention (/v1/realtime)./v1/realtime No 30 days None Yes No developers.openai.com/api/docs/guides/your-data Read 14 Nov 2026.
  132. OpenAI, other compliance statements: /v1/live/sessions: not used for training, 30-day abuse monitoring retention, eligible for Zero Data Retention with limitations (/v1/live/sessions (GPT-Live))./v1/live/sessions No 30 days None, or 30 days if stored Yes, with limitations below No developers.openai.com/api/docs/guides/your-data Read 14 Nov 2026.
  133. OpenAI, hIPAA agreement (BAA): A BAA for the API can be accepted self-serve without an enterprise agreement, once the organization has a history of API usage (API organizations).An enterprise agreement is not required to sign a BAA for API services. Self-serve enrollment requires an established history of API usage. help.openai.com/en/articles/8660679-getting-a-business-associate-agreement-for-the-openai-api Read 14 Nov 2026.
  134. OpenAI, hIPAA agreement (BAA): API use with PHI needs an executed BAA and Modified Retention provisioning, unless OpenAI specifies otherwise (API organizations).API HIPAA eligibility requires an executed OpenAI BAA. Your organization must also be provisioned with Modified Retention, unless OpenAI specifies otherwise. Once these requirements are met, you can use the endpoints below to process protected health information (PHI), even if data is retained. help.openai.com/en/articles/20001069-hipaa-eligible-products-and-functionality Read 14 Nov 2026.
  135. OpenAI, hIPAA agreement (BAA): /v1/realtime and /v1/live/sessions are on the list of HIPAA-eligible API endpoints (under an executed BAA with Modified Retention)./v1/completions /v1/realtime /v1/live/sessions help.openai.com/en/articles/20001069-hipaa-eligible-products-and-functionality Read 14 Nov 2026.