GPT Realtime 2.1 API Pricing / Price per 1M tokens
OpenAI • API Price Comparison
Also known as: gpt-realtime-2.1 · gptrealtime2.1 · gpt-realtime2.1 · gpt realtime2.1
Updated on · Published currencies / per 1M tokens; cheapest ranked by input
| Channel | Input / 1M | Output / 1M | Cache read / 1M | Updated / verified on |
|---|---|---|---|---|
| OpenAIOfficialLowest input | USD 32 | USD 64 | USD 0.4 | 2026-10-16 |
— means the price or date is not recorded. Cross-currency ranking uses exchange rates.
GPT Realtime 2.1 is a large language model by OpenAI with a 128K-token context window. Across the 1 API channels tracked here, input pricing ranges from $32.00 per 1M input tokens; the cheapest is OpenAI at $32.00 per 1M input tokens. The official channel (OpenAI) charges $32.00 per 1M input tokens and $64.00 per 1M output tokens. None of the tracked channels are directly reachable from mainland China without a proxy or VPN. Prices are collected daily from official provider pages and every tracked channel, then cross-checked by a data-accuracy audit.
| Usage Level | Tokens/Month | OpenAI |
|---|---|---|
| 🐣 Light | 0.1M in + 0.1M out | $6.40 |
| 📊 Medium | 1.0M in + 0.5M out | $64.00 |
| 🚀 Heavy | 10.0M in + 5.0M out | $640.00 |
| 🏢 Enterprise | 100.0M in + 50.0M out | $6,400.00 |
Frequently asked questions about gpt-realtime-2.1
How much does the GPT Realtime 2.1 API cost?
The lowest input rate is USD 32 per 1M tokens; output on that channel is USD 64 per 1M tokens.
Which channel has the cheapest GPT Realtime 2.1 API?
OpenAI has the lowest input rate: USD 32 per 1M tokens. Cross-currency ranking uses exchange rates; compare output and cache prices separately.
What is the GPT Realtime 2.1 cache-read price?
OpenAI: USD 0.4 per 1M cache-read tokens.
When was GPT Realtime 2.1 pricing last updated?
Updated on 2026-10-16. This is the latest recorded price update or verification; see the table for individual channel dates.
Related pricing research