What is the max output length for gpt-realtime-2?

gpt-realtime-2 supports up to 32000 output tokens per request. Plan your prompts to stay within this limit, and use the max_tokens or max_completion_tokens parameter to control output length.

What is the context window of GPT-Realtime-2?

GPT-Realtime-2 has a 128,000-token context window optimized for real-time voice interactions.

Does gpt-realtime-2 have a free tier?

GPT-Realtime-2 is billed per use and the record publishes no free-tier allowance. The current published rates are input $4.0000 per 1M tokens and output $24.0000 per 1M tokens. Trial credit or promotional quota is tied to your account rather than to the model, so check the console before planning around a free tier.

Can I use the OpenAI Realtime API to call GPT-Realtime-2?

Yes. Set the model parameter to “gpt-realtime-2” and use your MixRoute API key with the Realtime endpoint.

What are the rate limits for GPT-Realtime-2?

Rate limits for GPT-Realtime-2 depend on your MixRoute plan tier. Check your console quota.

Can you call GPT-Realtime-2 with the OpenAI SDK you already use?

Yes. GPT-Realtime-2 is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to gpt-realtime-2 . Keep your current request and response handling.

Does GPT-Realtime-2 support streaming output?

Yes. GPT-Realtime-2 is declared as supporting streamed responses.

Model detail

GPT-Realtime-2

Provided by OpenAI

Pay-as-you-go

An OpenAI realtime speech model combining configurable reasoning, instruction following, and tool use for more complex voice-agent interactions.

Model specs

Model ID: gpt-realtime-2

Context length: 128K
Max output: 32K
I/O modalities
Released: 2026-05

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$4.0000 /1M Tokens

Completion

$24.0000 /1M Tokens

Cache read

$0.4000 /1M Tokens

Image input

$5.0000 /1M Tokens

Audio input

$32.0000 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

An OpenAI realtime speech model combining configurable reasoning

An OpenAI realtime speech model combining configurable reasoning, instruction following, and tool use for more complex voice-agent interactions.

What should you check before using it?

Confirm audio formats, sample rates, and pricing

OpenAI model that supports reasoning, tool calling, streaming, prompt caching, vision input and the OpenAI SDK. Knowledge cutoff: 2024-09-30. Released 2026-05-07.

Why use it through MixRoute?

GPT-Realtime-2 cache reads cut repeated-prompt cost

Cached prefixes are billed at $0.4000 per 1M tokens instead of $4.0000 per 1M tokens for standard input, so repeated system prompts cost less. MixRoute serves GPT-Realtime-2 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID gpt-realtime-2 and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

GPT-Realtime-2 supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Streaming

GPT-Realtime-2 supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

GPT-Realtime-2 supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

Vision input

GPT-Realtime-2 can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

OpenAI SDK

Call GPT-Realtime-2 through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 128K

Output tokens Max per request 32K

Requests / month

Cache hit rate 0%

Share of the same prefix read repeatedly, up to 100%

FAQ

GPT-Realtime-2: An OpenAI realtime speech model combining configurable reasoning, instruction following, and tool use for more complex voice-agent interactions.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

gpt-realtime-2

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs