Cursor 支持来自 OpenAI、Anthropic、Google、SpaceXAI 等的最新一代模型。Pro、Pro Plus 和 Ultra 都包含两个用量池，方便你在智能水平、速度和成本之间找到合适的平衡。Start 是我们面向印度开发者推出的方案，涵盖 Cursor 模型用量池。
用量池¶
有两个独立的用量池，每个都会在你的月度计费周期重置：
- Cursor 模型：Cursor Grok 4.6、Grok 4.5 和 Composer 2.5 的包含用量显著更多。
- 其他模型：第三方模型的用量池，按模型的 API 价格计费。Pro、Pro Plus 和 Ultra 包含此用量池，并可根据需要额外付费购买用量。Start 方案不包含此用量池。
这两个用量池都可以在你的编辑器设置和你的用量仪表盘中查看。
Cursor 模型¶
Cursor 模型用量池包括 Cursor Grok 4.6、Grok 4.5 和 Composer 2.5。
在团队方案和企业版方案中，Cursor Router 会根据您的优化模式，为每个 Auto 请求选择模型。
| Model | Provider | Input | Cache write | Cache read | Output | Notes |
|---|---|---|---|---|---|---|
| Grok 4.6 | Cursor | $2 | - | $0.5 | $6 | Jointly trained by Cursor and SpaceXAI |
| Grok 4.6 (Fast) | Cursor | $4 | - | $1 | $12 | Jointly trained by Cursor and SpaceXAI |
| Grok 4.5 | Cursor | $2 | - | $0.5 | $6 | Jointly trained by Cursor and SpaceXAI |
| Grok 4.5 (Fast) | Cursor | $4 | - | $1 | $18 | Jointly trained by Cursor and SpaceXAI |
| Composer 2.5 | Cursor | $0.5 | - | $0.2 | $2.5 | - |
| Composer 2.5 (Fast) | Cursor | $3 | - | $0.5 | $15 | - |
其他模型¶
当你选择特定第三方模型时，用量会按该模型的 API 费率从 其他模型 用量池中扣减。
模型定价¶
所有价格均按每百万 token 计算：
| Model | Provider | Input | Cache write | Cache read | Output | Notes |
|---|---|---|---|---|---|---|
| Claude 4 Sonnet | Anthropic | $3 | $3.75 | $0.3 | $15 | Hidden by default; Thinking variant counts as 2 requests in legacy pricing |
| Claude 4 Sonnet 1M | Anthropic | $6 | $7.5 | $0.6 | $22.5 | Hidden by default; Thinking variant counts as 2 requests in legacy pricing; This model can be very expensive due to the large context window; The cost is 2x when the input exceeds 200k tokens |
| Claude 4.5 Haiku | Anthropic | $1 | $1.25 | $0.1 | $5 | Hidden by default; Bedrock/Vertex: regional endpoints +10% surcharge; Cache: writes 1.25x, reads 0.1x |
| Claude 4.5 Opus | Anthropic | $5 | $6.25 | $0.5 | $25 | Hidden by default; Requires Max Mode on legacy request-based plans |
| Claude 4.5 Sonnet | Anthropic | $3 | $3.75 | $0.3 | $15 | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) |
| Claude 4.6 Opus | Anthropic | $5 | $6.25 | $0.5 | $25 | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) |
| Claude 4.6 Sonnet | Anthropic | $3 | $3.75 | $0.3 | $15 | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) |
| Claude 4.7 Opus | Anthropic | $5 | $6.25 | $0.5 | $25 | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) |
| Claude Fable 5 | Anthropic | $10 | $12.5 | $1 | $50 | Requires data retention approval for Enterprise customers, Teams and individual customers with Privacy Mode enabled; Anthropic stores agent input and output data for harm-prevention processes; this data is not used to train or improve Anthropic models or products; Requests that trip a security guardrail are automatically routed to Claude Opus; About 2x the cost of Claude Opus 5; Requires Max Mode on legacy request-based plans |
| Claude Opus 4.7 (fast mode) | Anthropic | $30 | $37.5 | $3 | $150 | Hidden by default; Requires Max Mode on legacy request-based plans; Limited research preview; Up to 1M tokens with extended context at the same per-token rates as shorter context |
| Claude Opus 4.8 | Anthropic | $5 | $6.25 | $0.5 | $25 | Hidden by default; Requires Max Mode on legacy request-based plans; Fast mode (`claude-opus-4-8-fast`) requires Max Mode on legacy request-based plans; Fast mode is 3x lower per-token pricing than Opus 4.7 fast mode; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) |
| Claude Opus 5 | Anthropic | $5 | $6.25 | $0.5 | $25 | Requires Max Mode on legacy request-based plans; Fast mode (`claude-opus-5-fast`) requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) |
| Claude Sonnet 5 | Anthropic | $2 | $2.5 | $0.2 | $10 | Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge); Uses an updated tokenizer, so the same input can map to more tokens |
| Gemini 2.5 Flash | $0.3 | - | $0.03 | $2.5 | Hidden by default | |
| Gemini 3 Flash | $0.5 | - | $0.05 | $3 | Hidden by default | |
| Gemini 3 Pro | $2 | - | $0.2 | $12 | Hidden by default | |
| Gemini 3 Pro Image Preview | $2 | - | $0.2 | $12 | Hidden by default; Native image generation model optimized for speed, flexibility, and contextual understanding; Text input and output priced the same as Gemini 3 Pro; Image output: \(120/1M tokens (\~\)0.134 per 1K/2K image, \~$0.24 per 4K image); Preview models may change before becoming stable and have more restrictive rate limits | |
| Gemini 3.1 Pro | $2 | - | $0.2 | $12 | - | |
| Gemini 3.5 Flash | $1.5 | - | $0.15 | $9 | Hidden by default | |
| Gemini 3.6 Flash | $1.5 | - | $0.15 | $7.5 | Hidden by default | |
| Gemini 3.7 Flash | $0.75 | - | $0.075 | $3.5 | - | |
| GLM 5.2 | Z.ai | $1.4 | - | $0.26 | $4.4 | Hidden by default |
| GPT-5 | OpenAI | $1.25 | - | $0.125 | $10 | Hidden by default; Agentic and reasoning capabilities; Available reasoning effort variant is gpt-5-high |
| GPT-5 Fast | OpenAI | $2.5 | - | $0.25 | $20 | Hidden by default; Faster speed but 2x price; Available reasoning effort variants are gpt-5-high-fast, gpt-5-low-fast |
| GPT-5 Mini | OpenAI | $0.25 | - | $0.025 | $2 | Hidden by default |
| GPT-5-Codex | OpenAI | $1.25 | - | $0.125 | $10 | Hidden by default; Agentic and reasoning capabilities |
| GPT-5.1 Codex | OpenAI | $1.25 | - | $0.125 | $10 | Hidden by default; Agentic and reasoning capabilities |
| GPT-5.1 Codex Max | OpenAI | $1.25 | - | $0.125 | $10 | Hidden by default |
| GPT-5.1 Codex Mini | OpenAI | $0.25 | - | $0.025 | $2 | Hidden by default; Agentic and reasoning capabilities; 4x rate limits compared to GPT-5.1 Codex |
| GPT-5.2 | OpenAI | $1.75 | - | $0.175 | $14 | Hidden by default; Agentic and reasoning capabilities; Available reasoning effort variant is gpt-5.2-high |
| GPT-5.2 Codex | OpenAI | $1.75 | - | $0.175 | $14 | Hidden by default; Agentic and reasoning capabilities |
| GPT-5.3 Codex | OpenAI | $1.75 | - | $0.175 | $14 | Hidden by default; Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; Available reasoning effort variant is gpt-5.3-codex-high |
| GPT-5.4 | OpenAI | $2.5 | - | $0.25 | $15 | Hidden by default; Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; 90% discount on cached input tokens; Fast mode is 15% faster with 2x pricing; Long context supports up to 1M tokens with 2x input pricing |
| GPT-5.4 Mini | OpenAI | $0.75 | - | $0.075 | $4.5 | Hidden by default; Smaller, faster variant of GPT-5.4; 90% discount on cached input tokens |
| GPT-5.4 Nano | OpenAI | $0.2 | - | $0.02 | $1.25 | Hidden by default; Smallest GPT-5.4 variant, optimized for cost; 90% discount on cached input tokens |
| GPT-5.5 | OpenAI | $5 | - | $0.5 | $30 | Hidden by default; Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; More token-efficient than GPT-5.4 on comparable tasks; Improved persistence on long-running tasks; Fast mode is available at higher rates; Long context supports up to 1M tokens with 2x input pricing |
| GPT-5.6 Luna | OpenAI | $0.2 | $0.25 | $0.02 | $1.2 | Smallest GPT-5.6 variant, optimized for cost and speed; Agentic and reasoning capabilities; Fast mode is available at 2x pricing; Cache writes are billed at 1.25x the uncached input rate |
| GPT-5.6 Sol | OpenAI | $4 | $5 | $0.4 | $20 | Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; Fast mode is available at 2x pricing; Long context supports up to 1M tokens with 2x input pricing; Cache writes are billed at 1.25x the uncached input rate; Promotional pricing through November 21, 2026 |
| GPT-5.6 Terra | OpenAI | $2 | $2.5 | $0.2 | $12 | Mid-tier GPT-5.6 variant between Sol and Luna; Agentic and reasoning capabilities; Fast mode is available at 2x pricing; Cache writes are billed at 1.25x the uncached input rate |
| Kimi K2.7 Code | Moonshot | $0.95 | - | $0.19 | $4 | Hidden by default |
| Kimi K3 | Moonshot | $3 | - | $0.3 | $15 | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge); No separate cache-write fee |
选择使用区域数据驻留后，符合条件的模型定价将上浮 10%。有关支持的区域、模型、功能以及数据驻留策略的详细信息，请参阅 隐私与数据治理。
方案¶
Pro、Pro Plus 和 Ultra 都包含无限制的 Tab 补全、所有模型上的扩展智能体用量限额、对 Bugbot 的访问权限，以及对 Cloud Agents 的访问权限。Start 是面向印度开发者的低价方案，涵盖 Cursor 模型用量池和 Cloud Agents。
| 方案 | 价格 | Cursor 模型 | 其他模型 |
|---|---|---|---|
| Start (仅限印度) | ₹649/月，含税 | 包含 | 不包含 |
| Pro | $20/月 | 包含 | 包含 |
| Pro Plus | $60/月 | 包含 | 包含 |
| Ultra | $200/月 | 包含 | 包含 |
由于不同模型的 API 成本不同，你选择的模型会影响包含用量的消耗速度。
Start (仅限印度)¶
Start 面向印度开发者提供。每月 ₹649，含税；按月以 INR 通过 UPI、信用卡或借记卡付费。其他所有个人方案均显示未含税价格。
Start 包含充足的 Cursor 模型用量池额度，可满足你使用 Grok 4.6、Grok 4.5 和 Composer 2.5 进行日常开发的需求。在 Start 方案中，这三种模型均以非 Fast 模式运行，Grok 4.6 和 Grok 4.5 固定使用中等 effort 级别。你无法更改 effort 级别或在 Start 方案中启用 Fast 模式。升级到 Pro 或更高方案，即可选择 effort 级别和 Fast 模式。
Start 还包括 Cloud Agents、Cursor for iOS，以及插件、MCP 服务器、钩子和技能。
Start 不包括其他模型用量池、按需用量、Bugbot、Auto、自动化或 Cursor SDK。升级到 Pro 即可使用这些功能。更多详情请参阅 Cursor Start 公告。
我需要多少用量？¶
- 每天使用 Tab 的用户：通常可控制在包含用量以内
- 少量使用 Agent 的用户：通常可控制在包含用量以内
- 每天使用 Agent 的用户：每月总用量通常为 \(60–\)100
- 重度用户 (多个 Agent/自动化)：每月总用量通常为 $200 以上
当我达到限额时会发生什么？¶
当您超出每月包含的用量时，您可以：
- 添加按需用量：按相同的 API 费率继续使用，并按量付费
- 升级您的方案：升级到更高层级，获得更多包含用量
按需用量按月以相同费率计费。请求的质量和速度都不会降低。
Teams¶
目前有两种企业客户方案：Teams 和 企业版 (自定义报价)。Teams 提供两种席位类型：Standard (\(40/用户/月) 和 Premium (\)120/用户/月)，其中 Premium 的 Agent 限额是 Standard 的 5 倍。
团队方案提供额外功能，例如集中式团队计费和管理、用于内部规则、技能和插件的团队市场、借助 Bugbot 进行智能体驱动的代码评审、具备共享团队上下文的云端代理和自动化、使用分析、团队范围的隐私模式强制启用，以及 SAML/OIDC 单点登录。
对于乐于自助使用的客户，我们推荐 Teams。对于需要优先支持、共享用量、发票结算、SCIM 或高级安全控制的客户，我们推荐 企业版。
进一步了解 Teams 价格。
Cursor Token 费率¶
在团队方案和企业版方案中，第三方模型请求需支付每百万 token 0.25 美元的 Cursor Token 费率。该费率是在模型 API 定价之外额外收取的，适用于包含用量、按需用量和自带密钥 (BYOK) 用量。
当你直接选择第三方模型，以及当 Auto 路由到第三方模型时，都会适用 Cursor Token 费率。所有第一方 Cursor 模型 (包括 Grok 和 Composer) 均免收 Cursor Token 费率。
Auto 模式¶
Auto 有三种模式：Cost、Balance 和 Intelligence。
所有 Auto 模式均按每个请求路由至的模型标价计费。各模型的费率请参见 模型定价。第三方模型还需支付 Cursor Token 费率。
旧版企业版 Auto¶
截至 2026 年 9 月 7 日，企业版 Auto 的定价按每百万 token 固定，不受所用模型影响。
旧版基于请求的定价¶
Max Mode¶
Max Mode 仅适用于旧版基于请求的计费方案。它可将模型的上下文窗口扩展到默认上限以上，并按该模型的 API 费率加收 20%。详见 旧版方案中的 Max Mode。
常见问题¶
模型托管在哪里？¶
模型由模型提供商、可信赖的合作伙伴或 Cursor 托管。详情请参阅我们的 子处理方 列表。
在哪里可以找到定价条款？¶
有关企业版定价详情、计费条款和费用计算，请参阅 Pricing Policy。
