跳到主内容
智客 ZICQ

工具调用 (Function Call) 榜

智客 ZICQ 大模型榜单每日更新,覆盖智能、编程、价格与上下文,便于选型与比价。

最近更新:37 分钟前(2026-11-21 05:34)
清除
数据来源与评测方法

声明支持 tools / tool_choice 的模型,按 Agentic 指数 + 工具加成排序。

📊 评测基准与方法论说明
1. 数据来源:模型元数据与调用价格每小时自 OpenRouter (openrouter.ai) 官方接口同步,包含商业模型、开源权重及实验预览版本。
2. 评测基准:智能、编码与智能体指数直接源自第三方国际权威评测平台 Artificial Analysis (artificialanalysis.ai) 官方指标。
3. 综合榜权重:综合智能分 = 60% × 综合智力指数 + 25% × 代码生成指数 + 15% × 智能体与工具调用指数。无评测基准数据的模型排在综合榜末尾。
4. 推广链接:标注「推广」的「去调用」按钮是推广链接,ZICQ 可能因此获得佣金;推广关系不影响任何排名与评分。
当前筛选的统计
当前榜单模型数 476
免费可调 15
支持视觉 335
支持工具调用 414
支持推理 359
最长上下文 SpaceXSI: Grok 4.20 2M tokens
已知输入价格均值 $1.57 / 1M 美元 / 百万 token
最低价模型 inclusionAI: Ling 3.0 Tiny $0.015 / 1M
当前维度 TOP · 工具加成 Google: Gemini 4 Neon $-36.840
⚡ 模型并排 PK 对比器 & Token 成本计算器 点击下方任意模型的「+ PK 对比」即可替换 · 实时测算月度 API 成本 · 支持一键复制对比链接
对比维度 Google: Gemini 4 Neon Google DeepMind Google: Gemini 4 Neon (batch) Google DeepMind OpenAI: GPT-6.2 Astra Pro OpenAI
综合智能 / 编码 / 智能体 61.4 / 0.0 / 0.0 61.4 / 0.0 / 0.0 —
上下文窗口 1.0M tokens 1.0M tokens 1.1M tokens
输入 / 输出单价 (1M) $3.00 / $15.00 $1.50 / $7.50 $8.00 / $40.00
预估月度账单 (30天) 输入参数自动测算 输入参数自动测算 输入参数自动测算
  1. #181
    AionLabs: Aion-3.0-Mini Aion-Labs 通用大语言模型

    Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...

    工具 推理 结构化
    上下文 131K 输出 ≤ 32K
    $0.70/1M $1.40/1M 输出 cache $0.18/1M
    Function Call 稳定
  2. #182
    AionLabs: Aion-3.0 Aion-Labs 通用大语言模型

    Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

    工具 推理 结构化
    上下文 131K 输出 ≤ 32K
    $3.00/1M $6.00/1M 输出 cache $0.75/1M
    Function Call 稳定
  3. #183
    Tencent: Hy3 Tencent 通用大语言模型

    Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

    工具 推理 结构化
    上下文 262K 输出 ≤ 128K
    $0.08/1M $0.33/1M 输出 cache $0.02/1M
    Function Call 稳定
  4. #184
    Anthropic: Claude Sonnet 5 Anthropic 文档视觉模型

    Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $2.00/1M $10.00/1M 输出 cache $0.20/1M
    Function Call 稳定
  5. #185
    Anthropic: Claude Sonnet 5 (batch) Anthropic 文档视觉模型

    Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $1.00/1M $5.00/1M 输出 cache $0.10/1M
    Function Call 稳定
  6. #186
    Sakana: Fugu Ultra Sakana 视觉多模态

    Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

    工具 视觉 推理 结构化 联网
    上下文 1M 输出 ≤ 128K
    $5.00/1M $30.00/1M 输出 cache $0.50/1M
    Function Call 稳定
  7. #187
    Google: Nano Banana Pro (Gemini 3 Pro Image) Google DeepMind 图像生成

    Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

    工具 视觉 推理 结构化 生图
    上下文 131K 输出 ≤ 32K
    $2.00/1M $12.00/1M 输出 cache $0.20/1M
    Function Call 稳定
  8. #188
    Z.ai: GLM 5.2 Zhipu 智谱 通用大语言模型

    GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

    工具 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $0.62/1M $2.42/1M 输出 cache $0.14/1M
    Function Call 稳定
  9. #189
    Z.ai: GLM 5.2 (batch) Zhipu 智谱 通用大语言模型

    GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

    工具 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $0.32/1M $0.99/1M 输出 cache $0.11/1M
    Function Call 稳定
  10. #190
    MoonshotAI: Kimi K2.7 Code Moonshotai 视觉多模态

    MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

    工具 视觉 推理 结构化
    上下文 262K 输出 ≤ 235K
    $0.60/1M $3.00/1M 输出 cache $0.12/1M
    Function Call 稳定
  11. #191
    Anthropic: Claude Fable Latest ~Anthropic 文档视觉模型

    This model always redirects to the latest model in the Claude Fable family.

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $8.00/1M $40.00/1M 输出 cache $0.20/1M
    Function Call 稳定
  12. #192
    Anthropic: Claude Fable 5 Anthropic 文档视觉模型

    Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $10.00/1M $50.00/1M 输出 cache $1.00/1M
    Function Call 稳定
  13. #193
    Anthropic: Claude Fable 5 (batch) Anthropic 文档视觉模型

    Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $5.00/1M $25.00/1M 输出 cache $0.50/1M
    Function Call 稳定
  14. #194
    NVIDIA: Nemotron 3 Ultra NVIDIA 通用大语言模型 有基准

    NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    工具 推理 结构化
    上下文 262K 输出 ≤ 16K
    $0.50/1M $2.20/1M 输出 cache $0.10/1M
    Function Call 稳定
  15. #195
    NVIDIA: Nemotron 3 Ultra (free) NVIDIA 通用大语言模型 免费 有基准

    NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    工具 推理
    上下文 1M 输出 ≤ 65K
    免费
    免费可调 · 限时白嫖
  16. #196
    Qwen: Qwen3.7 Plus Alibaba 通义 视觉多模态

    Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

    工具 视觉 推理 结构化
    上下文 1M 输出 ≤ 131K
    $0.32/1M $1.28/1M 输出 cache $0.06/1M
    Function Call 稳定
  17. #197
    Qwen: Qwen3.7 Plus (batch) Alibaba 通义 视觉多模态

    Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

    工具 视觉 推理 结构化
    上下文 262K 输出 ≤ 131K
    $0.23/1M $0.92/1M 输出
    Function Call 稳定
  18. #198
    MiniMax: MiniMax M3 MiniMax 视觉多模态 有基准

    MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

    工具 视觉 视频 推理 结构化
    上下文 1.0M 输出 ≤ 512K
    $0.30/1M $1.20/1M 输出 cache $0.06/1M
    Function Call 稳定
  19. #199
    MiniMax: MiniMax M3 (batch) MiniMax 视觉多模态 有基准

    MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

    工具 视觉 视频 推理 结构化
    上下文 524K 输出 ≤ 512K
    $0.22/1M $0.88/1M 输出 cache $0.04/1M
    Function Call 稳定
  20. #200
    StepFun: Step 3.7 Flash Stepfun 视觉多模态

    Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

    工具 视觉 视频 推理 结构化
    上下文 262K 输出 ≤ 230K
    $0.20/1M $1.15/1M 输出 cache $0.04/1M
    Function Call 稳定