智能体与工具调用榜
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:43 分钟前(2026-11-20 05:59)数据来源与评测方法
依据 OpenRouter benchmarks.agentic_index(智能体 / 工具调用指数),结合 supported_parameters.tools 标记,给做 Agent 框架的极客参考。
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
⚡ 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 | Anthropic: Claude Fable 5.2 Anthropic | Anthropic: Claude Fable 5.2 (batch) Anthropic | OpenAI: GPT-6.2 Astra OpenAI |
|---|---|---|---|
| 综合智能 / 编码 / 智能体 | 64.6 / 0.0 / 0.0 | 64.6 / 0.0 / 0.0 | 62.1 / 0.0 / 0.0 |
| 上下文窗口 | 1M tokens | 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 |
-
#201
GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$2.00/1M $12.00/1M 输出 cache $0.20/1M工具调用能力扎实 -
#202
GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$1.00/1M $6.00/1M 输出 cache $0.10/1M工具调用能力扎实 -
#203
GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$4.00/1M $20.00/1M 输出 cache $0.40/1M工具调用能力扎实 -
#204
GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$2.00/1M $10.00/1M 输出 cache $0.20/1M工具调用能力扎实 -
#205
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$4.00/1M $20.00/1M 输出 cache $0.40/1M工具调用能力扎实 -
#206
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$2.00/1M $10.00/1M 输出 cache $0.20/1M工具调用能力扎实 -
#207
Grok 4.5 is a model from xAI with frontier performance on coding, knowledge work, and STEM.
工具 视觉 文档 推理 结构化上下文 500K 输出 ≤ 450K$2.00/1M $6.00/1M 输出 cache $0.30/1M工具调用能力扎实 -
#208
This model always redirects to the latest Grok model from xAI.
工具 视觉 文档 推理 结构化上下文 500K 输出 ≤ 450K$2.00/1M $6.00/1M 输出 cache $0.50/1M工具调用能力扎实 -
#209
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工具调用能力扎实 -
#210
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工具调用能力扎实 -
#211
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工具调用能力扎实 -
#212
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工具调用能力扎实 -
#213
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工具调用能力扎实 -
#214
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...
视觉 推理 结构化 生图上下文 65K 输出 ≤ 58K$0.25/1M $1.50/1M 输出工具调用能力扎实 -
#215
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工具调用能力扎实 -
#216
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...
视觉 推理 结构化 生图上下文 131K 输出 ≤ 32K$0.50/1M $3.00/1M 输出工具调用能力扎实 -
#217
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工具调用能力扎实 -
#218
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工具调用能力扎实 -
#219
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工具调用能力扎实 -
#220
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$0.65/1M $3.50/1M 输出 cache $0.16/1M工具调用能力扎实