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:51 分钟前(2026-11-19 03:12)
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 478
免费可调 17
支持视觉 334
支持工具调用 415
支持推理 361
最长上下文 xAI: Grok 4.20 2M tokens
已知输入价格均值 $1.55 / 1M 美元 / 百万 token
最低价模型 Z.ai: GLM 5.2 $0.007 / 1M
当前维度 TOP · 工具加成 OpenAI: GPT-6.2 Astra Pro $-0.000
⚡ 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 OpenAI: GPT-6.2 Astra Pro OpenAI OpenAI: GPT-6.2 Astra Pro (batch) OpenAI OpenAI: GPT-6.2 Astra OpenAI
综合智能 / 编码 / 智能体 — — 62.1 / 0.0 / 0.0
上下文窗口 1.1M tokens 1.1M tokens 1.1M tokens
输入 / 输出单价 (1M) $8.00 / $40.00 $4.00 / $20.00 $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. #41
    DeepSeek: DeepSeek V4.1 Flash 1017 (batch) DeepSeek 视觉多模态 有基准

    DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

    工具 视觉 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $0.04/1M $0.15/1M 输出 cache $0.00/1M
    Function Call 稳定
  2. #42
    Elorian: Glimpse Elorian 视觉多模态

    Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...

    工具 视觉 视频 推理 结构化
    上下文 262K 输出 ≤ 256K
    $0.60/1M $3.00/1M 输出 cache $0.06/1M
    Function Call 稳定
  3. #43
    Reflection: Beam 1.0 501B A23B Reflection 通用大语言模型 有基准

    Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

    工具 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $0.30/1M $1.00/1M 输出 cache $0.04/1M
    Function Call 稳定
  4. #44
    PrismML: Ternary Bonsai 2 9B Prism-Ml 视觉多模态

    Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...

    工具 视觉 推理 结构化
    上下文 262K 输出 ≤ 65K
    $0.08/1M $0.13/1M 输出 cache $0.04/1M
    Function Call 稳定
  5. #45
    Meta: Muse Spark Open Meta 音视频多模态 有基准

    Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

    工具 视觉 音频 视频 文档 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $1.25/1M $4.25/1M 输出 cache $0.15/1M
    Function Call 稳定
  6. #46
    NVIDIA: Nemotron 3.5 Super VL NVIDIA 视觉多模态 有基准

    NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    工具 视觉 视频 推理 结构化
    上下文 1.0M 输出 ≤ 235K
    $0.15/1M $0.50/1M 输出 cache $0.02/1M
    Function Call 稳定
  7. #47
    NVIDIA: Nemotron 3.5 Super VL (free) NVIDIA 视觉多模态 免费 有基准

    NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    工具 视觉 视频 推理 结构化
    上下文 1M 输出 ≤ 131K
    免费
    免费可调 · 限时白嫖
  8. #48
    Pareto 26.10 Unbiased 视觉多模态

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

    工具 视觉
    上下文 1.0M 输出 ≤ 131K
    $0.80/1M $3.20/1M 输出 cache $0.03/1M
    Function Call 稳定
  9. #49
    Pareto Latest ~Unbiased 视觉多模态

    This model always redirects to the latest model in the Pareto family.

    工具 视觉
    上下文 1.0M 输出 ≤ 131K
    $0.80/1M $3.20/1M 输出 cache $0.03/1M
    Function Call 稳定
  10. #50
    Pareto 26.9 Unbiased 视觉多模态

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

    工具 视觉 结构化
    上下文 262K 输出 ≤ 131K
    $2.50/1M $7.50/1M 输出 cache $0.25/1M
    Function Call 稳定
  11. #51
    LiquidAI: LFM2.5-24B-A2B Liquid 通用大语言模型

    LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

    工具 推理 结构化
    上下文 128K 输出 ≤ 8K
    $0.05/1M $0.70/1M 输出 cache $0.02/1M
    Function Call 稳定
  12. #52
    Google: Gemini 4 Argon Google DeepMind 音视频多模态 有基准

    Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

    工具 视觉 音频 视频 文档 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $2.00/1M $10.00/1M 输出 cache $0.10/1M
    Function Call 稳定
  13. #53
    Google: Gemini 4 Argon (batch) Google DeepMind 音视频多模态 有基准

    Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

    工具 视觉 音频 视频 文档 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $1.00/1M $5.00/1M 输出 cache $0.05/1M
    Function Call 稳定
  14. #54
    Meta: Muse Wonder Meta 音视频多模态 有基准

    Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

    工具 视觉 音频 视频 文档 推理 结构化
    上下文 1.0M 输出 ≤ 943K
    $4.00/1M $20.00/1M 输出 cache $0.20/1M
    Function Call 稳定
  15. #55
    StepFun: Step 5 Preview Stepfun 视觉多模态 有基准

    Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...

    工具 视觉 视频 推理 结构化
    上下文 1M 输出 ≤ 64K
    $1.00/1M $2.70/1M 输出 cache $0.10/1M
    Function Call 稳定
  16. #56
    Anthropic: Claude Haiku 5.5 Anthropic 文档视觉模型 有基准

    Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $0.10/1M $0.50/1M 输出 cache $0.01/1M
    Function Call 稳定
  17. #57
    Anthropic: Claude Haiku 5.5 (batch) Anthropic 文档视觉模型 有基准

    Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $0.05/1M $0.25/1M 输出 cache $0.01/1M
    Function Call 稳定
  18. #58
    Google: Nano Banana 2.1 Google DeepMind 图像生成

    Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

    工具 视觉 推理 结构化 生图
    上下文 65K 输出 ≤ 58K
    $1.50/1M $7.50/1M 输出
    Function Call 稳定
  19. #59
    Mistral: Mistral Large 4 Mistral AI 视觉多模态 有基准

    Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

    工具 视觉 推理 结构化
    上下文 1.0M 输出 ≤ 262K
    $0.70/1M $2.10/1M 输出 cache $0.07/1M
    Function Call 稳定
  20. #60
    inclusionAI: Ling 3.1 Flash Inclusionai 通用大语言模型 有基准

    Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

    工具 推理
    上下文 1M 输出 ≤ 262K
    $0.04/1M $0.14/1M 输出 cache $0.01/1M
    Function Call 稳定