LLM ReferenceLLM Reference

gpt-realtime-1.5

gpt-realtime-1.5

ProprietaryMultimodal

About

Best voice model for audio in / audio out in the Realtime API. Replaces deprecated gpt-4o-realtime-preview models (shut down May 7, 2026). Supports text, audio, and image inputs.

gpt-realtime-1.5 has a 32K-token context window.

gpt-realtime-1.5 input tokens at $4/1M, output at $16/1M.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudioFine-tuning

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
OpenAI API$4.00$16.00Serverless

Rankings

Best AI Agents & Agentic ModelsBest Multimodal / Vision LLMsBest LLMs for Function Calling & Tool UseCheapest LLM APIsBest LLM APIsBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support

Specifications

FamilyGPT Realtime
Released2026-05-07
Context32K
Max output4,096
ArchitectureDecoder Only
Knowledge cutoff2024-09
Specializationgeneral
LicenseProprietary
Trainingpretrained

Created by

OpenAIOpenAI

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website

Providers(1)

OpenAI API