import { AIChatModelCard } from '../types/aiModel'; const aihubmixModels: AIChatModelCard[] = [ { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 400_000, description: 'GPT-5 pro 使用更多计算来更深入地思考，并持续提供更好的答案。', displayName: 'GPT-5 pro', id: 'gpt-5-pro', maxOutput: 272_000, pricing: { units: [ { name: 'textInput', rate: 15, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 120, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-10-06', settings: { extendParams: ['textVerbosity'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 400_000, description: 'GPT-5 Codex 是一个针对 Codex 或类似环境中的代理编码任务优化的 GPT-5 版本。', displayName: 'GPT-5 Codex', id: 'gpt-5-codex', maxOutput: 128_000, pricing: { units: [ { name: 'textInput', rate: 1.25, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 10, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.125, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2024-09-15', settings: { extendParams: ['gpt5ReasoningEffort', 'textVerbosity'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 400_000, description: '跨领域编码和代理任务的最佳模型。GPT-5 在准确性、速度、推理、上下文识别、结构化思维和问题解决方面实现了飞跃。', displayName: 'GPT-5', enabled: true, id: 'gpt-5', maxOutput: 128_000, pricing: { units: [ { name: 'textInput', rate: 1.25, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 10, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.125, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-08-07', settings: { extendParams: ['gpt5ReasoningEffort', 'textVerbosity'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 400_000, description: '更快、更经济高效的 GPT-5 版本，适用于明确定义的任务。在保持高质量输出的同时，提供更快的响应速度。', displayName: 'GPT-5 mini', enabled: true, id: 'gpt-5-mini', maxOutput: 128_000, pricing: { units: [ { name: 'textInput', rate: 0.25, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 2, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.025, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-08-07', settings: { extendParams: ['gpt5ReasoningEffort', 'textVerbosity'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, vision: true, }, contextWindowTokens: 400_000, description: '最快、最经济高效的 GPT-5 版本。非常适合需要快速响应且成本敏感的应用场景。', displayName: 'GPT-5 nano', id: 'gpt-5-nano', maxOutput: 128_000, pricing: { units: [ { name: 'textInput', rate: 0.05, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.01, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-08-07', settings: { extendParams: ['gpt5ReasoningEffort', 'textVerbosity'], }, type: 'chat', }, { abilities: { reasoning: true, structuredOutput: false, vision: true, }, contextWindowTokens: 400_000, description: 'ChatGPT 中使用的 GPT-5 模型。结合了强大的语言理解与生成能力，适合对话式交互应用。', displayName: 'GPT-5 Chat', enabled: true, id: 'gpt-5-chat-latest', maxOutput: 128_000, pricing: { units: [ { name: 'textInput', rate: 1.25, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 10, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.125, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-08-07', type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 200_000, description: 'o4-mini 是我们最新的小型 o 系列模型。 它专为快速有效的推理而优化，在编码和视觉任务中表现出极高的效率和性能。', displayName: 'o4-mini', id: 'o4-mini', maxOutput: 100_000, pricing: { units: [ { name: 'textInput', rate: 1.1, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 4.4, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.275, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-04-17', settings: { extendParams: ['reasoningEffort'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 200_000, description: 'o4-mini-deep-research 是我们更快速、更实惠的深度研究模型——非常适合处理复杂的多步骤研究任务。它可以从互联网上搜索和综合信息，也可以通过 MCP 连接器访问并利用你的自有数据。', displayName: 'o4-mini Deep Research', id: 'o4-mini-deep-research', maxOutput: 100_000, pricing: { units: [ { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 8, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-06-26', settings: { extendParams: ['reasoningEffort'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 200_000, description: 'o3-pro 模型使用更多的计算来更深入地思考并始终提供更好的答案，仅支持 Responses API 下使用。', displayName: 'o3-pro', id: 'o3-pro', maxOutput: 100_000, pricing: { units: [ { name: 'textInput', rate: 20, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 80, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-06-10', settings: { extendParams: ['reasoningEffort'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 200_000, description: 'o3 是一款全能强大的模型，在多个领域表现出色。它为数学、科学、编程和视觉推理任务树立了新标杆。它也擅长技术写作和指令遵循。用户可利用它分析文本、代码和图像，解决多步骤的复杂问题。', displayName: 'o3', id: 'o3', maxOutput: 100_000, pricing: { units: [ { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 8, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-04-16', settings: { extendParams: ['reasoningEffort'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 200_000, description: 'o3-deep-research 是我们最先进的深度研究模型，专为处理复杂的多步骤研究任务而设计。它可以从互联网上搜索和综合信息，也可以通过 MCP 连接器访问并利用你的自有数据。', displayName: 'o3 Deep Research', id: 'o3-deep-research', maxOutput: 100_000, pricing: { units: [ { name: 'textInput', rate: 10, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 40, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 2.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-06-26', settings: { extendParams: ['reasoningEffort'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, search: true, vision: true, }, contextWindowTokens: 1_047_576, description: 'GPT-4.1 是我们用于复杂任务的旗舰模型。它非常适合跨领域解决问题。', displayName: 'GPT-4.1', id: 'gpt-4.1', maxOutput: 32_768, pricing: { units: [ { name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 8, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-04-14', settings: { searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, search: true, vision: true, }, contextWindowTokens: 1_047_576, description: 'GPT-4.1 mini 提供了智能、速度和成本之间的平衡，使其成为许多用例中有吸引力的模型。', displayName: 'GPT-4.1 mini', id: 'gpt-4.1-mini', maxOutput: 32_768, pricing: { units: [ { name: 'textInput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 1.6, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-04-14', settings: { searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, vision: true, }, contextWindowTokens: 1_047_576, description: 'GPT-4.1 nano 是最快，最具成本效益的GPT-4.1模型。', displayName: 'GPT-4.1 nano', id: 'gpt-4.1-nano', maxOutput: 32_768, pricing: { units: [ { name: 'textInput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.025, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-04-14', type: 'chat', }, { abilities: { vision: true, }, contextWindowTokens: 128_000, description: 'ChatGPT-4o 是一款动态模型，实时更新以保持当前最新版本。它结合了强大的语言理解与生成能力，适合于大规模应用场景，包括客户服务、教育和技术支持。', displayName: 'ChatGPT-4o', id: 'chatgpt-4o-latest', pricing: { units: [ { name: 'textInput', rate: 5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 15, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, search: true, vision: true, }, contextWindowTokens: 2_000_000, description: '我们很高兴发布 Grok 4 Fast，这是我们在成本效益推理模型方面的最新进展。', displayName: 'Grok 4 Fast (Non-Reasoning)', id: 'grok-4-fast-non-reasoning', pricing: { units: [ { name: 'textInput', rate: 0.2, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-09-09', settings: { searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 2_000_000, description: '我们很高兴发布 Grok 4 Fast，这是我们在成本效益推理模型方面的最新进展。', displayName: 'Grok 4 Fast', id: 'grok-4-fast-reasoning', pricing: { units: [ { name: 'textInput', rate: 0.2, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-09-09', settings: { searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, vision: true, }, contextWindowTokens: 256_000, description: 'Grok最新旗舰模型，在自然语言、数学和推理方面提供了无与伦比的性能——堪称完美的‘多面手’。 当前指向模型版本为grok-4-0709；注意该模型由于资源有限暂时比官方贵 10% 预计后续会降至官方原价。', displayName: 'Grok 4 0709', enabled: true, id: 'grok-4', pricing: { units: [ { name: 'textInput', rate: 3.3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 16.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-07-09', type: 'chat', }, { abilities: { functionCall: true, }, contextWindowTokens: 131_072, description: '旗舰级模型，擅长数据提取、编程和文本摘要等企业级应用，拥有金融、医疗、法律和科学等领域的深厚知识。', displayName: 'Grok 3', id: 'grok-3', pricing: { units: [ { name: 'textInput', rate: 3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 15, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.75, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-04-03', type: 'chat', }, { abilities: { functionCall: true, reasoning: true, }, contextWindowTokens: 131_072, description: '轻量级模型，回话前会先思考。运行快速、智能，适用于不需要深层领域知识的逻辑任务，并能获取原始的思维轨迹。', displayName: 'Grok 3 Mini', id: 'grok-3-mini', pricing: { units: [ { name: 'textInput', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-04-03', settings: { extendParams: ['reasoningEffort'], }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 200_000, description: 'Claude Opus 4.1 是 Anthropic 最新的用于处理高度复杂任务的最强大模型。它在性能、智能、流畅性和理解力方面表现卓越。', displayName: 'Claude Opus 4.1', enabled: true, id: 'claude-opus-4-1-20250805', maxOutput: 32_000, pricing: { units: [ { name: 'textInput', rate: 16.5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 82.5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 1.5, strategy: 'fixed', unit: 'millionTokens' }, { lookup: { prices: { '5m': 20.625 }, pricingParams: ['ttl'] }, name: 'textInput_cacheWrite', strategy: 'lookup', unit: 'millionTokens', }, ], }, releasedAt: '2025-08-05', settings: { extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 200_000, description: 'Claude Opus 4 是 Anthropic 用于处理高度复杂任务的最强大模型。它在性能、智能、流畅性和理解力方面表现卓越。', displayName: 'Claude Opus 4', id: 'claude-opus-4-20250514', maxOutput: 32_000, pricing: { units: [ { name: 'textInput', rate: 16.8, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 84, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 1.5, strategy: 'fixed', unit: 'millionTokens' }, { lookup: { prices: { '5m': 20.625 }, pricingParams: ['ttl'] }, name: 'textInput_cacheWrite', strategy: 'lookup', unit: 'millionTokens', }, ], }, releasedAt: '2025-05-23', settings: { extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 200_000, description: 'Sonnet 4.5 是世界上最好的代理、编码和计算机使用模型。它也是我们在长时间运行任务中最准确、最详细的模型，具有增强的编码、金融和网络安全领域知识。', displayName: 'Claude Sonnet 4.5', enabled: true, id: 'claude-sonnet-4-5-20250929', maxOutput: 64_000, pricing: { units: [ { name: 'textInput', rate: 3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 15, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' }, { lookup: { prices: { '1h': 6, '5m': 3.75 }, pricingParams: ['ttl'] }, name: 'textInput_cacheWrite', strategy: 'lookup', unit: 'millionTokens', }, ], }, releasedAt: '2025-09-29', settings: { extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 200_000, description: 'Claude Sonnet 4 可以产生近乎即时的响应或延长的逐步思考，用户可以清晰地看到这些过程。API 用户还可以对模型思考的时间进行细致的控制', displayName: 'Claude Sonnet 4', id: 'claude-sonnet-4-20250514', maxOutput: 64_000, pricing: { units: [ { name: 'textInput', rate: 3.3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 16.5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' }, { lookup: { prices: { '5m': 4.125 }, pricingParams: ['ttl'] }, name: 'textInput_cacheWrite', strategy: 'lookup', unit: 'millionTokens', }, ], }, releasedAt: '2025-05-23', settings: { extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 200_000, description: 'Claude 3.7 Sonnet 是 Anthropic 迄今为止最智能的模型，也是市场上首个混合推理模型。Claude 3.7 Sonnet 可以产生近乎即时的响应或延长的逐步思考，用户可以清晰地看到这些过程。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。', displayName: 'Claude 3.7 Sonnet', id: 'claude-3-7-sonnet-20250219', maxOutput: 64_000, pricing: { units: [ { name: 'textInput', rate: 3.3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 16.5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' }, { lookup: { prices: { '5m': 4.125 }, pricingParams: ['ttl'] }, name: 'textInput_cacheWrite', strategy: 'lookup', unit: 'millionTokens', }, ], }, releasedAt: '2025-02-24', settings: { extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 200_000, description: 'Claude Haiku 4.5 是 Anthropic 最快且最智能的 Haiku 模型，具有闪电般的速度和扩展思考能力。', displayName: 'Claude Haiku 4.5', enabled: true, id: 'claude-haiku-4-5-20251001', maxOutput: 64_000, pricing: { units: [ { name: 'textInput', rate: 1, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' }, { lookup: { prices: { '1h': 2, '5m': 1.25 }, pricingParams: ['ttl'] }, name: 'textInput_cacheWrite', strategy: 'lookup', unit: 'millionTokens', }, ], }, releasedAt: '2025-10-16', settings: { extendParams: ['disableContextCaching', 'enableReasoning', 'reasoningBudgetToken'], searchImpl: 'params', }, type: 'chat', }, { abilities: { functionCall: true, vision: true, }, contextWindowTokens: 200_000, description: 'Claude 3.5 Haiku 是 Anthropic 最快的下一代模型。与 Claude 3 Haiku 相比，Claude 3.5 Haiku 在各项技能上都有所提升，并在许多智力基准测试中超越了上一代最大的模型 Claude 3 Opus。', displayName: 'Claude 3.5 Haiku', id: 'claude-3-5-haiku-20241022', maxOutput: 8192, pricing: { units: [ { name: 'textInput', rate: 1.1, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 5.5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' }, { lookup: { prices: { '5m': 1.1 }, pricingParams: ['ttl'] }, name: 'textInput_cacheWrite', strategy: 'lookup', unit: 'millionTokens', }, ], }, releasedAt: '2024-11-05', settings: { extendParams: ['disableContextCaching'], }, type: 'chat', }, { abilities: { functionCall: true, }, contextWindowTokens: 131_072, description: 'DeepSeek V3.2 是 DeepSeek 最新发布的通用大模型，支持混合推理架构，具备更强的 Agent 能力。', displayName: 'DeepSeek V3.2 Exp', id: 'DeepSeek-V3.2-Exp', maxOutput: 8192, pricing: { units: [ { name: 'textInput', rate: 0.28, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.42, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-09-29', type: 'chat', }, { abilities: { functionCall: true, reasoning: true, }, contextWindowTokens: 131_072, description: 'DeepSeek V3.2 思考模式。在输出最终回答之前，模型会先输出一段思维链内容，以提升最终答案的准确性。', displayName: 'DeepSeek V3.2 Exp Thinking', enabled: true, id: 'DeepSeek-V3.2-Exp-Think', maxOutput: 65_536, pricing: { units: [ { name: 'textInput', rate: 0.28, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.42, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-09-29', type: 'chat', }, { abilities: { functionCall: true, }, contextWindowTokens: 131_072, description: 'DeepSeek-V3.1-非思考模式；DeepSeek-V3.1 是深度求索全新推出的混合推理模型，支持思考与非思考2种推理模式，较 DeepSeek-R1-0528 思考效率更高。经 Post-Training 优化，Agent 工具使用与智能体任务表现大幅提升。', displayName: 'DeepSeek V3.1 (non-Think)', id: 'DeepSeek-V3.1', pricing: { units: [ { name: 'textInput', rate: 0.56, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 1.68, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, }, contextWindowTokens: 131_072, description: 'DeepSeek-V3.1-思考模式；DeepSeek-V3.1 是深度求索全新推出的混合推理模型，支持思考与非思考2种推理模式，较 DeepSeek-R1-0528 思考效率更高。经 Post-Training 优化，Agent 工具使用与智能体任务表现大幅提升。', displayName: 'DeepSeek V3.1 (Think)', id: 'DeepSeek-V3.1-Think', pricing: { units: [ { name: 'textInput', rate: 0.56, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 1.68, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, }, contextWindowTokens: 131_072, description: 'DeepSeek V3.1 Fast 是 DeepSeek V3.1版本的高TPS极速版。 混合思考模式：通过更改聊天模板，一个模型可以同时支持思考模式和非思考模式。 更智能的工具调用：通过后训练优化，模型在工具使用和代理任务中的表现显著提升。', displayName: 'DeepSeek V3.1 (Fast)', id: 'DeepSeek-V3.1-Fast', pricing: { units: [ { name: 'textInput', rate: 1.096, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 3.288, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, structuredOutput: true, }, contextWindowTokens: 131_072, description: '已升级至最新版本250528；字节火山云开源部署的满血 R1，总参数量 671B，输入最高 64k。目前最稳定，推荐用这个。', displayName: 'DeepSeek R1', id: 'DeepSeek-R1', pricing: { units: [ { name: 'textInput', rate: 0.546, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 2.184, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, }, contextWindowTokens: 65_536, description: '由微软部署提供； DeepSeek R1型号已进行小版本升级，当前版本为DeepSeek-R1-0528。在最新的更新中，DeepSeek R1通过增加计算资源和引入后训练阶段的算法优化机制，大幅提升了推理深度和推断能力。该模型在数学、编程和通用逻辑等多个基准测试中表现出色，其整体性能已接近领先模型，如O3和Gemini 2.5 Pro 。', displayName: 'DeepSeek R1 0528 (Azure)', id: 'azure-DeepSeek-R1-0528', pricing: { units: [ { name: 'textInput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 1.6, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, }, contextWindowTokens: 131_072, description: '字节火山云开源部署目前最稳定，推荐用这个。已经自动升级为最新发布的版本 250324 。', displayName: 'DeepSeek V3', id: 'DeepSeek-V3', pricing: { units: [ { name: 'textInput', rate: 0.272, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 1.088, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, }, contextWindowTokens: 65_536, description: '模型供应商为：sophnet平台。DeepSeek V3 Fast 是 DeepSeek V3 0324 版本的高TPS极速版，满血非量化，代码与数学能力更强，响应更快！', displayName: 'DeepSeek V3 (Fast)', id: 'DeepSeek-V3-Fast', pricing: { units: [ { name: 'textInput', rate: 0.55, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 2.2, strategy: 'fixed', unit: 'millionTokens' }, ], }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 1_048_576 + 65_536, description: 'Gemini 2.5 Pro 是 Google 最先进的思维模型，能够对代码、数学和STEM领域的复杂问题进行推理，以及使用长上下文分析大型数据集、代码库和文档。', displayName: 'Gemini 2.5 Pro', enabled: true, id: 'gemini-2.5-pro', maxOutput: 65_536, pricing: { units: [ { name: 'textInput', rate: 1.25, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 10, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-06-17', settings: { extendParams: ['thinkingBudget', 'urlContext'], searchImpl: 'params', searchProvider: 'google', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, structuredOutput: true, vision: true, }, contextWindowTokens: 1_048_576 + 65_536, description: 'Gemini 2.5 Flash 是 Google 性价比最高的模型，提供全面的功能。', displayName: 'Gemini 2.5 Flash', id: 'gemini-2.5-flash', maxOutput: 65_536, pricing: { units: [ { name: 'textInput', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 2.5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.075, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-06-17', settings: { extendParams: ['thinkingBudget', 'urlContext'], searchImpl: 'params', searchProvider: 'google', }, type: 'chat', }, { abilities: { imageOutput: true, vision: true, }, contextWindowTokens: 32_768 + 8192, description: 'Nano Banana 是 Google 最新、最快、最高效的原生多模态模型，它允许您通过对话生成和编辑图像。', displayName: 'Nano Banana', enabled: true, id: 'gemini-2.5-flash-image', maxOutput: 8192, pricing: { units: [ { name: 'textInput', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'imageInput', rate: 0.3, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 2.5, strategy: 'fixed', unit: 'millionTokens' }, { name: 'imageOutput', rate: 30, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-08-26', type: 'chat', }, { abilities: { functionCall: true, reasoning: true, search: true, vision: true, }, contextWindowTokens: 1_048_576 + 65_536, description: 'Gemini 2.5 Flash-Lite 是 Google 最小、性价比最高的模型，专为大规模使用而设计。', displayName: 'Gemini 2.5 Flash-Lite', id: 'gemini-2.5-flash-lite', maxOutput: 65_536, pricing: { units: [ { name: 'textInput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.4, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textInput_cacheRead', rate: 0.025, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-07-22', settings: { extendParams: ['thinkingBudget', 'urlContext'], searchImpl: 'params', searchProvider: 'google', }, type: 'chat', }, { abilities: { functionCall: true, reasoning: true, }, contextWindowTokens: 131_072, description: '基于Qwen3的思考模式开源模型，相较上一版本（通义千问3-235B-A22B）逻辑能力、通用能力、知识增强及创作能力均有大幅提升，适用于高难度强推理场景。', displayName: 'Qwen3 235B A22B Thinking 2507', id: 'qwen3-235b-a22b-thinking-2507', maxOutput: 32_768, organization: 'Qwen', pricing: { currency: 'CNY', units: [ { name: 'textInput', rate: 0.28, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 2.8, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-07-25', type: 'chat', }, { abilities: { functionCall: true, }, contextWindowTokens: 131_072, description: '基于Qwen3的非思考模式开源模型，相较上一版本（通义千问3-235B-A22B）主观创作能力与模型安全性均有小幅度提升。', displayName: 'Qwen3 235B A22B Instruct 2507', id: 'qwen3-235b-a22b-instruct-2507', maxOutput: 32_768, organization: 'Qwen', pricing: { currency: 'CNY', units: [ { name: 'textInput', rate: 0.28, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 1.12, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-07-22', type: 'chat', }, { abilities: { functionCall: true, reasoning: true, }, contextWindowTokens: 131_072, description: '基于Qwen3的思考模式开源模型，相较上一版本（通义千问3-30B-A3B）逻辑能力、通用能力、知识增强及创作能力均有大幅提升，适用于高难度强推理场景。', displayName: 'Qwen3 30B A3B Thinking 2507', id: 'qwen3-30b-a3b-thinking-2507', maxOutput: 32_768, organization: 'Qwen', pricing: { currency: 'CNY', units: [ { name: 'textInput', rate: 0.12, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 1.2, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-07-30', type: 'chat', }, { abilities: { functionCall: true, }, contextWindowTokens: 131_072, description: '相较上一版本（Qwen3-30B-A3B）中英文和多语言整体通用能力有大幅提升。主观开放类任务专项优化，显著更加符合用户偏好，能够提供更有帮助性的回复。', displayName: 'Qwen3 30B A3B Instruct 2507', id: 'qwen3-30b-a3b-instruct-2507', maxOutput: 32_768, organization: 'Qwen', pricing: { currency: 'CNY', units: [ { name: 'textInput', rate: 0.12, strategy: 'fixed', unit: 'millionTokens' }, { name: 'textOutput', rate: 0.48, strategy: 'fixed', unit: 'millionTokens' }, ], }, releasedAt: '2025-07-29', type: 'chat', }, ]; export default aihubmixModels;