Model Catalog › openai

gpt-realtime-2.1

gpt-realtime-2.1

SPEECH High tier Speech Proprietary (API-only)

gpt-realtime-2.1 (gpt-realtime-2.1) is a speech model from openai with a 128K-token context window; proprietary (API-only); capabilities tools, vision, reasoning; input audio, image, text; output audio, text.

128KContext
32KMax output
$4$ / 1M in

Pricing

Input
$4 / 1M tokens
Output
$24 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.

Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.

Specifications

Context window
128,000 tokens (128K)
Max output
32,000 tokens
Weights
Proprietary (API-only)
Input modalities
audio image text
Output modalities
audio text
Knowledge cutoff
2024-09-30
Release date
2026-07-06

Capabilities

tools vision reasoning

Provenance

committedlitellmmodels-devopenai-api
Last verified: 2026-10-30

Related models

gpt-audio-1.5
gpt-audio-1.5
openai · SPEECH · 128K ctx
gpt-audio-2025-08-28
gpt-audio-2025-08-28
openai · SPEECH · 128K ctx
gpt-audio-mini
gpt-audio-mini
openai · SPEECH · 128K ctx
gpt-audio-mini-2025-10-06
gpt-audio-mini-2025-10-06
openai · SPEECH · 128K ctx
gpt-audio-mini-2025-12-15
gpt-audio-mini-2025-12-15
openai · SPEECH · 128K ctx
gpt-realtime-2.1-mini
gpt-realtime-2.1-mini
openai · SPEECH · 128K ctx