AI API Model Intelligence
ModelPort Hub：选模型、比价格，一站接入 AI API
查清主流模型的价格、上下文、视觉与函数调用能力，快速完成横向比较；选定模型后，通过 ModelPort API 使用统一入口开始调用。
Best Coding LLM
Rank AI API models for coding, debugging, refactoring, and code review.
Cheapest AI API
Rank low-cost AI API models by token price and cost efficiency.
Best Chinese LLM
Rank AI models for Chinese writing, Chinese QA, and localized workflows.
Best Function Calling Models
Rank models for tool calling, agent workflows, and structured outputs.
Best Vision LLM
Rank multimodal AI models for screenshots, images, and visual QA.
ModelPort API
选好模型后，直接开始调用
使用模型页、价格页和排行榜完成选择，再进入 ModelPort API 创建密钥，通过一个入口调用多个主流模型。
Popular
热门模型
OpenAI
GPT-5.1
High-end general reasoning model for agents and production apps.
- 价格
- $4.50 in / $13.50 out
- 上下文
- 256K tokens
Anthropic
Claude 4.6 Sonnet
Careful long-form reasoning model with strong writing and coding balance.
- 价格
- $3.00 in / $15.00 out
- 上下文
- 200K tokens
DeepSeek
DeepSeek V4
Cost-efficient reasoning and coding model for high-volume API traffic.
- 价格
- $0.350 in / $1.40 out
- 上下文
- 128K tokens
Leaderboard
模型排行榜
| Rank | 模型 | 价格 | 上下文 | 目录评分* |
|---|---|---|---|---|
| #1 | GPT-5.1 OpenAI | $4.50 in / $13.50 out | 256K tokens | 72/100 |
| #2 | DeepSeek V4 DeepSeek | $0.350 in / $1.40 out | 128K tokens | 98/100 |
| #3 | Claude 4.6 Sonnet Anthropic | $3.00 in / $15.00 out | 200K tokens | 76/100 |
| #4 | Qwen 3.5 Max Alibaba Cloud | $0.800 in / $2.40 out | 128K tokens | 92/100 |
| #5 | Gemini 3 Pro | $2.50 in / $10.00 out | 1M tokens | 79/100 |
| #6 | Mistral Large 3 Mistral AI | $2.00 in / $6.00 out | 128K tokens | 84/100 |
* 目录评分用于候选模型排序，基于编辑判断与目录能力信号，不代表独立 benchmark 成绩。生产选型请使用自己的任务集复测。
Latest
最新模型
Other
Auto Router (Beta)
Auto Router (Beta) model profile with source-linked pricing, context, capabilities, and API details.
- 价格
- $-1000000.000 in / $-1000000.000 out
- 上下文
- 2M tokens
Other
Meta: Muse Spark 1.1
Meta: Muse Spark 1.1 model profile with source-linked pricing, context, capabilities, and API details.
- 价格
- $1.25 in / $4.25 out
- 上下文
- 1.048576M tokens
Other
MoonshotAI: Kimi K3
MoonshotAI: Kimi K3 model profile with source-linked pricing, context, capabilities, and API details.
- 价格
- $3.00 in / $15.00 out
- 上下文
- 1.048576M tokens
Other
Z.ai: GLM 5.2
Z.ai: GLM 5.2 model profile with source-linked pricing, context, capabilities, and API details.
- 价格
- $0.419 in / $1.32 out
- 上下文
- 1.048576M tokens
Compare
热门对比
DeepSeek V4 vs Claude 4.6 Sonnet
DeepSeek V4 is stronger on API cost and Chinese workloads, while Claude 4.6 Sonnet is stronger for careful code editing, long-form reasoning, and analysis-heavy writing.
GPT-5.1 vs Gemini 3 Pro
GPT-5.1 is the better default for agentic reasoning and tool use, while Gemini 3 Pro stands out for very long context and multimodal search-like workflows.
GPT-5.1 vs Claude 4.6 Sonnet
GPT-5.1 和 Claude 4.6 Sonnet 的 API 价格、上下文长度、视觉能力、函数调用和适用场景对比。
GPT-5.1 vs DeepSeek V4
GPT-5.1 和 DeepSeek V4 的 API 价格、上下文长度、视觉能力、函数调用和适用场景对比。