Claude Opus 4.1

claude-opus-4-1

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Flagship Claude model for deep reasoning, coding, and long-horizon agents

200K context200K context

Released2025-08-05

Relays12 sites

reasoningcode generationlong contexttool use

Model information

Model ID: claude-opus-4-1
Context: 200K
Max input: -
Max output: 32K
Knowledge cutoff: 2025-03-31
Open weights: Not supported
License: -
Release date: 2025-08-05

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: Supported

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

sidrune

https://sidrune.ai/Token billing

Price range ¥37.5 - ¥67.5 / 1M tokens

Claude-AWSB-Sale

Cache hit¥3.75

Cache write¥75

Claude-AWSB-Premium

Cache write¥126

Claude-Anthropic官

Cache hit¥6.75

Cache write¥135

Channel	Billing	Input	Output	Cache hit	Cache write
Claude-AWSB-Sale	Token	¥37.5	¥187.5	¥3.75	¥75
Claude-AWSB-Premium	Token	¥63	¥315	¥6.3	¥126
Claude-Anthropic官	Token	¥67.5	¥337.5	¥6.75	¥135

aiaimark

https://www.aiaimark.comToken billing

Price range ¥7.5 / 1M tokens

claude-优惠分组

Cache hit¥0.75

Cache write¥15

claude-优惠分组

Cache hit¥0.75

Cache write¥15

Channel	Billing	Input	Output	Cache hit	Cache write
claude-优惠分组	Token	¥7.5	¥37.5	¥0.75	¥15
claude-优惠分组	Token	¥7.5	¥37.5	¥0.75	¥15

天才程序员

gptapis.xyzToken billing

Price range ¥15 / 1M tokens

Cache write¥30

Channel	Billing	Input	Output	Cache hit	Cache write
ccmax	Token	¥15	¥75	¥1.5	¥30

LinoRoute

linoroute.comToken billing

Price range ¥9.71 - ¥36.3 / 1M tokens

Cache hit¥0.9706

Cache write¥12.13

Cache hit¥3.63

Cache write¥45.38

Channel	Billing	Input	Output	Cache hit	Cache write
Claude-Code-2	Token	¥9.71	¥48.53	¥0.9706	¥12.13
AWS-Claude-3	Token	¥36.3	¥181.5	¥3.63	¥45.38

XycAi(星道智能)

https://xycai.us/Token billing

Price range ¥101.43 / 1M tokens

Claude 工作流

Cache hit¥10.14

Cache write¥126.79

Claude 工作流

Cache hit¥10.14

Cache write¥126.79

Channel	Billing	Input	Output	Cache hit	Cache write
Claude 工作流	Token	¥101.43	¥507.15	¥10.14	¥126.79
Claude 工作流	Token	¥101.43	¥507.15	¥10.14	¥126.79

迈威AI

mxwell.aiToken billing

Price range ¥24 / 1M tokens

Claude-Max-满血

Cache write¥30

Channel	Billing	Input	Output	Cache hit	Cache write
Claude-Max-满血	Token	¥24	¥120	¥2.4	¥30

VovoKey｜启界

vovokey.comToken billing

Price range ¥72 / 1M tokens

Claude-ASW-Bedrock-全模型企业

Cache write¥144

Channel	Billing	Input	Output	Cache hit	Cache write
Claude-ASW-Bedrock-全模型企业	Token	¥72	¥360	¥7.2	¥144

夯炸了AI

api.hangzhale.comToken billing

Price range ¥16.5 / 1M tokens

Claude-Max-外接

Cache hit¥1.65

Cache write¥20.63

Channel	Billing	Input	Output	Cache hit	Cache write
Claude-Max-外接	Token	¥16.5	¥82.5	¥1.65	¥20.63

橙子AI

api.orange30.topToken billing

Price range ¥6 - ¥12 / 1M tokens

Cache write¥12

Cache write¥24

Channel	Billing	Input	Output	Cache hit	Cache write
group-45	Token	¥6	¥30	¥0.6	¥12
group-34	Token	¥12	¥60	¥1.2	¥24

ePhone AI

ephone.aiToken billing

Price range ¥15.75 - ¥55.65 / 1M tokens

Cache hit¥1.57

Cache write¥31.5

Cache hit¥3.67

Cache write¥73.5

claude-official-cheap

Cache hit¥5.57

Cache write¥111.3

Channel	Billing	Input	Output	Cache hit	Cache write
claude-mix	Token	¥15.75	¥78.75	¥1.57	¥31.5
claude-cc	Token	¥36.75	¥183.75	¥3.67	¥73.5
claude-official-cheap	Token	¥55.65	¥278.25	¥5.57	¥111.3

How should Claude Opus 4.1 relay pricing be compared?

This Claude Opus 4.1 pricing page compares official pricing with public prices from 12 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: 11/08/2026, 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.