How much does GPT-Realtime-2.1 cost per month?

For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, GPT-Realtime-2.1 costs about $4,800 per month at OpenAI's list prices ($4.00 per 1M input tokens, $24.00 per 1M output tokens).

Does GPT-Realtime-2.1 support prompt caching?

Yes. Cached input costs $0.40 per 1M tokens, compared with $4.00 for regular input.

How long is GPT-Realtime-2.1's context window?

GPT-Realtime-2.1 accepts up to 128,000 tokens (128K) of context and returns up to 32,000 tokens per response.

GPT-Realtime-2.1 API Pricing

OpenAI · released Jul 6, 2026 · 128K context · API model ID gpt-realtime-2.1

GPT-Realtime-2.1 by OpenAI API pricing: $4.00 per 1M input tokens and $24.00 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).

Prices

GPT-Realtime-2.1 prices, USD per 1M tokens
Price	USD per 1M tokens
Input	$4.00
Output	$24.00
Cache read	$0.40
Cache write	Not published
Audio input	$32.00
Audio output	$64.00

OpenAI's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation

Estimated monthly cost

$4,800

per month

per day: $160.00
per request: $0.016

Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.

Compare this workload across models

Monthly cost by workload

Workload	Per month
Chatbot1,000 in / 500 out tokens, 10,000 requests a day	$4,800/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day	$6,600/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input	$3,120/mo

Context and capabilities

Context: 128,000 tokens
Max output: 32,000 tokens
Input: text, audio, image
Output: text, audio
Knowledge cutoff: Sep 30, 2024
Open weights: No
Tool calling: Yes
Reasoning: Yes
Structured outputs: No

Capabilities and limits as listed by models.dev.

Similarly priced models

Claude Opus 5.5 · $4.00 in / $20.00 out
Kimi K3 · $3.00 in / $15.00 out
Gemini 3.1 Pro Preview · $2.00 in / $12.00 out
GPT-6 Astra · $10.00 in / $50.00 out

Price history

No price changes since we started tracking on Oct 8, 2026.

Questions

How much does GPT-Realtime-2.1 cost per month?: For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, GPT-Realtime-2.1 costs about $4,800 per month at OpenAI's list prices ($4.00 per 1M input tokens, $24.00 per 1M output tokens).
Does GPT-Realtime-2.1 support prompt caching?: Yes. Cached input costs $0.40 per 1M tokens, compared with $4.00 for regular input.
How long is GPT-Realtime-2.1's context window?: GPT-Realtime-2.1 accepts up to 128,000 tokens (128K) of context and returns up to 32,000 tokens per response.