Price range ¥0.45 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| default | Token | ¥0.45 | ¥2.68 | - | - |
GPT-Realtime-2.1
gpt-realtime-2.1A real-time speech-to-speech model for configurable reasoning, tool use, and robust voice agents.
Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior
128K context128K context
Released2026-07-06
Relays3 sites
audioreasoningtool use
Model information
- Model ID
- gpt-realtime-2.1
- Context
- 128K
- Max input
- 96K
- Max output
- 32K
- Knowledge cutoff
- 2024-09-30
- Open weights
- Not supported
- License
- -
- Release date
- 2026-07-06
Input
Text: SupportedImage: SupportedAudio: SupportedVideo: Not supportedPDF: Not supportedFile: Supported
Output
Text: SupportedImage: Not supportedAudio: SupportedVideo: Not supported
API capabilities
Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported
OpenAI Official Pricing
CNYUpdated: 2026-10-04T22:55:12.731+08:00
Input
~¥26.757/ 1M tokens
Output
~¥160.544/ 1M tokens
Cache read
~¥2.676/ 1M tokens
Relay Comparison
Compare token, per-request, or per-second pricing by relay channel.
Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit
Price range ¥0.52 - ¥0.56 / 1M tokens
CodeX-不降智
BillingToken
Input¥0.52
Output¥3.12
Cache hit¥0.052
Cache write-
GPT-Pro-不降智
BillingToken
Input¥0.52
Output¥3.12
Cache hit¥0.052
Cache write-
GPT-福利分组
BillingToken
Input¥0.56
Output¥3.36
Cache hit¥0.056
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| CodeX-不降智 | Token | ¥0.52 | ¥3.12 | ¥0.052 | - |
| GPT-Pro-不降智 | Token | ¥0.52 | ¥3.12 | ¥0.052 | - |
| GPT-福利分组 | Token | ¥0.56 | ¥3.36 | ¥0.056 | - |
openai-official-cheap
BillingToken
Input¥14.84
Output¥89.04
Cache hit¥1.48
Cache write-
azure
BillingToken
Input¥28
Output¥168
Cache hit¥2.8
Cache write-
openai
BillingToken
Input¥28
Output¥168
Cache hit¥2.8
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| openai-official-cheap | Token | ¥14.84 | ¥89.04 | ¥1.48 | - |
| azure | Token | ¥28 | ¥168 | ¥2.8 | - |
| openai | Token | ¥28 | ¥168 | ¥2.8 | - |
How should GPT-Realtime-2.1 relay pricing be compared?
This GPT-Realtime-2.1 pricing page compares official pricing with public prices from 3 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 10/23/2026, 08:15.
- Data sources
- Public price catalogs, official pricing records, and monitoring results.
- Metric definitions
- Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
- Risk note
- Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.