{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/gpt-realtime-2/","md":"https://postcutoff.com/m/gpt-realtime-2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"gpt-realtime-2","name":"GPT-Realtime-2","org":"OpenAI","family":"GPT Realtime","released":"2026-05-07","status":"current","type":"audio/speech","modality_in":["text","audio","image"],"modality_out":["text","audio"],"open_weights":false,"model_license":"proprietary","context_window":128000,"max_output":32000,"knowledge_cutoff":"2024-09","pricing":{"text_input":4,"text_output":24,"audio_input":32,"audio_output":64,"cached_input":0.4,"image_input":5,"unit":"per 1M tokens (USD); cached audio/text input $0.40, cached image $0.50","source":"https://developers.openai.com/api/docs/pricing"},"price_line":"$4 text in, $24 text out per 1M tokens","access":[{"provider":"OpenAI API","model_id":"gpt-realtime-2","endpoint":"wss://api.openai.com/v1/realtime","docs":"https://developers.openai.com/api/docs/models/gpt-realtime-2"}],"capabilities":[{"name":"Reasoning speech-to-speech model","detail":"First OpenAI realtime voice model with configurable reasoning effort (press: 'GPT-5-class' reasoning); higher effort adds latency and tokens.","first":false,"discovered":"launch","source":"https://developers.openai.com/api/docs/models/gpt-realtime-2"},{"name":"128K-token realtime context","detail":"Context grew from 32K (gpt-realtime-1.5) to 128K tokens, with 32K max output, for long voice-agent sessions.","first":false,"discovered":"launch","source":"https://www.ghacks.net/2026/05/11/openai-releases-three-new-realtime-voice-models-for-the-api-with-gpt-5-class-reasoning/"}],"entry":"2026-05-07-openai-gpt-realtime-2-translate-whisper","notes":"Launched 2026-05-07 with gpt-realtime-translate and gpt-realtime-whisper (changelog). Superseded two months later by gpt-realtime-2.1 (2026-07-06) at identical prices, but still listed and not deprecated. Realtime endpoint only; function calling and prompt caching. Official launch post (openai.com) returned 403 to our fetcher, so benchmark claims were not read directly; secondary sources quote OpenAI: +15.2% Big Bench Audio vs gpt-realtime-1.5 (high effort), +13.8% Audio MultiChallenge instruction following (xhigh); one blog reports 96.6% absolute Big Bench Audio at xhigh (unconfirmed).","verified":"2026-09-29","body_md":"OpenAI's first reasoning realtime voice model. For new builds prefer [gpt-realtime-2.1](gpt-realtime-2-1.md).\n\nSources:\n- https://developers.openai.com/api/docs/models/gpt-realtime-2\n- https://developers.openai.com/api/docs/pricing\n- https://developers.openai.com/api/docs/changelog\n- https://openai.com/index/advancing-voice-intelligence-with-new-models-in-the-api/","page_url":"https://postcutoff.com/m/gpt-realtime-2/","standing":{"kind":"speech and audio","newer_count":57,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"gpt-audio-1-5","name":"GPT-Audio-1.5 (and gpt-audio / gpt-audio-mini)","org":"OpenAI","released":"2026-02-23","page_url":"https://postcutoff.com/m/gpt-audio-1-5/"},"after":{"id":"gpt-realtime-2-1","name":"GPT-Realtime-2.1","org":"OpenAI","released":"2026-07-06","page_url":"https://postcutoff.com/m/gpt-realtime-2-1/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}