o3

o3

A deliberate o-series reasoner for hard math, coding, and multi-step analysis.

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

200K context200K context

Released2025-04-16

Relays11 sites

reasoningcode generation

Model information

Model ID: o3
Context: 200K
Max input: -
Max output: 100K
Knowledge cutoff: 2024-05
Open weights: Not supported
License: -
Release date: 2025-04-16

Input

Text: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported

Output

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported

OpenAI Official Pricing

CNY

Updated: 2026-10-04T22:55:13.099+08:00

Input

~¥13.379/ 1M tokens

Output

~¥53.515/ 1M tokens

Cache read

~¥3.345/ 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

9527code

https://9527.codesToken billing

Price range ¥6 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
Azure-GPT	Token	¥6	¥24	¥1.5	-

找模型

api.zhaomoxing.comToken billing

Price range ¥3 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
Azure-GPT	Token	¥3	¥12	-	-

token2u

https://token2u.ai/r/hovyToken billing

Price range ¥14 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
official-cheap	Token	¥14	¥56	¥3.5	-

模方

api.modelscube.comToken billing

Price range ¥0.26 - ¥0.28 / 1M tokens

CodeX-不降智

Cache hit¥0.065

GPT-Pro-不降智

Cache hit¥0.065

GPT-福利分组

Cache hit¥0.07

Channel	Billing	Input	Output	Cache hit	Cache write
CodeX-不降智	Token	¥0.26	¥1.04	¥0.065	-
GPT-Pro-不降智	Token	¥0.26	¥1.04	¥0.065	-
GPT-福利分组	Token	¥0.28	¥1.12	¥0.07	-

XycAi(星道智能)

https://xycai.us/Token billing

Price range ¥13.52 / 1M tokens

Cache hit¥3.38

Channel	Billing	Input	Output	Cache hit	Cache write
GPT 工作流	Token	¥13.52	¥54.1	¥3.38	-

LinoRoute

linoroute.comToken billing

Price range ¥0.176 - ¥0.88 / 1M tokens

Cache hit¥0.044

Cache hit¥0.22

Channel	Billing	Input	Output	Cache hit	Cache write
Azure-Gpt-1	Token	¥0.176	¥0.704	¥0.044	-
Azure-Gpt-2	Token	¥0.4	¥1.6	¥0.1	-
Azure-Gpt-3	Token	¥0.88	¥3.52	¥0.22	-

ClaudeCN

claudecn.topToken billing

Price range ¥14 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
正价Openai	Token	¥14	¥56	¥3.5	-

RunAPI

https://runapi.hostToken billing

Price range ¥8.1 - ¥12.15 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥8.1	¥32.4	-	-
Plus	Token	¥12.15	¥48.6	-	-

AIGC Token

aigc-token.comToken billing

Price range ¥1.2 - ¥2 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
Azure	Token	¥1.2	¥4.8	¥0.3	-
AzurePlus	Token	¥2	¥8	¥0.5	-
default	Token	¥2	¥8	¥0.5	-

Super API

superapi.buzzToken billing

Price range ¥1.6 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
openai-官key	Token	¥1.6	¥6.4	¥0.4	-

How should o3 relay pricing be compared?

This o3 pricing page compares official pricing with public prices from 11 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, 08:14.

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.