跳到主内容
智客 ZICQ

长上下文榜

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:59 分钟前(2026-11-19 05:12)
清除
数据来源与评测方法

按 context_length 倒序 —— 适合长文档阅读、整库分析、百万级 token 任务。

📊 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 479
免费可调 17
支持视觉 335
支持工具调用 416
支持推理 362
最长上下文 xAI: Grok 4.20 Multi-Agent 2M tokens
已知输入价格均值 $1.56 / 1M 美元 / 百万 token
最低价模型 inclusionAI: Ling 3.0 Tiny $0.015 / 1M
当前维度 TOP · 上下文长度 xAI: Grok 4.20 Multi-Agent 2M
⚡ 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 xAI: Grok 4.20 Multi-Agent xAI xAI: Grok 4.20 xAI Auto Router Openrouter
综合智能 / 编码 / 智能体 — — —
上下文窗口 2M tokens 2M tokens 2M tokens
输入 / 输出单价 (1M) $1.25 / $2.50 $1.25 / $2.50 $-1000000.00 / $-1000000.00
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. #321
    Mistral: Ministral 3 8B 2512 Mistral AI 视觉多模态

    A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

    工具 视觉 结构化
    上下文 262K 输出 ≤ 209K
    $0.15/1M $0.15/1M 输出 cache $0.01/1M
    长文档处理首选
  2. #322
    Mistral: Mistral Large 3 2512 Mistral AI 文档视觉模型

    Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

    工具 视觉 文档 结构化
    上下文 262K 输出 ≤ 209K
    $0.50/1M $1.50/1M 输出 cache $0.05/1M
    长文档处理首选
  3. #323
    MoonshotAI: Kimi K2 Thinking Moonshotai 通用大语言模型

    Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

    工具 推理 结构化
    上下文 262K 输出 ≤ 98K
    $0.60/1M $2.50/1M 输出 cache $0.15/1M
    长文档处理首选
  4. #324
    Qwen: Qwen3 VL 8B Instruct Alibaba 通义 视觉多模态

    Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

    工具 视觉 结构化
    上下文 262K 输出 ≤ 235K
    $0.25/1M $0.75/1M 输出 cache $0.12/1M
    长文档处理首选
  5. #325
    Qwen: Qwen3 VL 30B A3B Instruct Alibaba 通义 视觉多模态

    Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

    工具 视觉 结构化
    上下文 262K 输出 ≤ 16K
    $0.15/1M $0.60/1M 输出
    长文档处理首选
  6. #326
    Qwen: Qwen3 VL 235B A22B Instruct Alibaba 通义 视觉多模态

    Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

    工具 视觉 结构化
    上下文 262K 输出 ≤ 32K
    $0.21/1M $1.90/1M 输出 cache $0.10/1M
    长文档处理首选
  7. #327
    Qwen: Qwen3 Next 80B A3B Instruct Alibaba 通义 通用大语言模型

    Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

    工具 结构化
    上下文 262K 输出 ≤ 235K
    $0.10/1M $1.10/1M 输出 cache $0.07/1M
    长文档处理首选
  8. #328
    MoonshotAI: Kimi K2 0905 Moonshotai 通用大语言模型

    Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

    工具 结构化
    上下文 262K 输出 ≤ 98K
    $0.60/1M $2.50/1M 输出
    长文档处理首选
  9. #329
    Qwen: Qwen3 Coder 30B A3B Instruct Alibaba 通义 代码编程

    Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

    工具 结构化
    上下文 262K 输出 ≤ 235K
    $0.15/1M $0.60/1M 输出
    长文档处理首选
  10. #330
    Qwen: Qwen3 30B A3B Instruct 2507 Alibaba 通义 通用大语言模型

    Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

    工具 结构化
    上下文 262K 输出 ≤ 235K
    $0.10/1M $0.30/1M 输出 cache $0.10/1M
    长文档处理首选
  11. #331
    Qwen: Qwen3 Coder 480B A35B Alibaba 通义 代码编程

    Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

    工具 结构化
    上下文 262K 输出 ≤ 65K
    $0.30/1M $1.00/1M 输出 cache $0.10/1M
    长文档处理首选
  12. #332
    Qwen: Qwen3 235B A22B Instruct 2507 Alibaba 通义 通用大语言模型

    Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

    工具 结构化
    上下文 262K 输出 ≤ 117K
    $0.14/1M $0.80/1M 输出 cache $0.05/1M
    长文档处理首选
  13. #333
    Morph: Morph V3 Large Morph 通用大语言模型

    Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

    结构化
    上下文 262K 输出 ≤ 131K
    $0.90/1M $1.90/1M 输出
    长文档处理首选
  14. #334
    Morph: Morph V3 Large (batch) Morph 通用大语言模型

    Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

    结构化
    上下文 262K 输出 ≤ 131K
    $0.45/1M $0.95/1M 输出
    长文档处理首选
  15. #335
    Morph: Morph V3 Fast Morph 通用大语言模型

    Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

    结构化
    上下文 262K 输出 ≤ 131K
    $0.80/1M $1.20/1M 输出
    长文档处理首选
  16. #336
    KT: Mi:dm K 3.0 Pro Kt 通用大语言模型

    Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.

    工具 推理 结构化
    上下文 261K 输出 ≤ 235K
    $0.20/1M $0.80/1M 输出 cache $0.04/1M
    长文档处理首选
  17. #337
    Cohere: North Mini Code (free) Cohere 代码编程 免费 有基准

    North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

    工具 推理
    上下文 256K 输出 ≤ 64K
    免费
    免费可调 · 限时白嫖
  18. #338
    xAI: Grok Build 0.1 xAI 文档视觉模型

    Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

    工具 视觉 文档 推理 结构化
    上下文 256K 输出 ≤ 230K
    $1.00/1M $2.00/1M 输出 cache $0.20/1M
    长文档处理首选
  19. #339
    NVIDIA: Nemotron 3 Nano Omni (free) NVIDIA 音视频多模态 免费

    NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

    工具 视觉 音频 视频 推理
    上下文 256K 输出 ≤ 65K
    免费
    免费可调 · 限时白嫖
  20. #340
    Relace: Relace Search Relace 通用大语言模型

    The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

    工具 结构化
    上下文 256K 输出 ≤ 128K
    $1.00/1M $3.00/1M 输出
    长文档处理首选