AIsa LLM 模型目录 - API Endpoint、能力和上下文窗口

AIsa 的 Model Gateway 可以通过一个 API Key 路由 LLM 和媒体生成请求。本指南是面向 Agent 的稳定 Markdown 来源，适合需要了解 AIsa 支持哪些模型 ID、每个模型使用哪个 endpoint，以及各模型能力边界的场景。实时模型目录在 aisa.one/models。下方表格基于 2026 年 6 月 4 日的 Model Gateway 在线元数据刷新。模型可用性和价格可能变化，生产路由前请以实时模型目录为最终来源。

如何调用模型

使用 AISA_API_KEY 作为 Bearer token。对于 OpenAI 兼容 SDK，将 base URL 设置为 https://api.aisa.one/v1。

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AISA_API_KEY"],
    base_url="https://api.aisa.one/v1"
)

response = client.chat.completions.create(
    model="qwen3.7-max",
    messages=[{"role": "user", "content": "Compare these model options for a coding agent."}]
)
print(response.choices[0].message.content)

Endpoint 类型

Endpoint	当前模型数量
`POST /v1/chat/completions`	55
`POST /v1/messages`	10
`POST /v1/responses`	4
`POST /v1/images/generations`	1
`POST /v1beta/models/{model}:generateContent`	1

大多数文本、视觉、音频、代码和多模态模型使用 POST /v1/chat/completions。Claude 模型也可能提供 Anthropic 兼容的 POST /v1/messages。部分模型提供 POST /v1/responses、Gemini 兼容的 POST /v1beta/models/{model}:generateContent，或图像生成路由。调用时请始终使用下表中的精确模型字符串。

能力标签说明

能力	在 AIsa Model Gateway 中的含义
Text	自然语言生成、摘要、分析、翻译和长上下文推理。
Coding	代码推理、代码补全、软件 Agent 规划和工具调用流程。
Vision	图像/文档理解、视觉编码，以及基于视觉输入的空间推理。
Audio	上游模型支持时的音频理解或语音到语音交互。
Image	图像生成、图像编辑、图像一致性，或在图像中渲染文字。
Video	视频理解、时序推理、长视频处理、图生视频或全模态/视频流程。

Provider 概览

Provider	模型数量	能力	示例模型 ID
OpenAI	8	Coding, Text, Vision, Image	`gpt-5`, `gpt-5-mini`, `gpt-5.2`, `gpt-5.2-chat-latest` …
Anthropic	7	Coding, Text, Vision	`claude-haiku-4-5-20251001`, `claude-opus-4-1-20250805`, `claude-opus-4-5-20251101`, `claude-opus-4-6` …
Google Gemini	2	Text	`gemini-3-pro-preview`, `gemini-3.5-flash`
xAI	4	Text, Vision, Coding	`grok-4.20-0309-non-reasoning`, `grok-4.20-0309-reasoning`, `grok-4.3`, `grok-build-0.1`
DeepSeek	6	Coding, Text	`deepseek-r1`, `deepseek-v3`, `deepseek-v3.1`, `deepseek-v3.2` …
Alibaba	16	Audio, Coding, Text, Video, Vision, Image	`qwen-flash`, `qwen-mt-flash`, `qwen-mt-lite`, `qwen-plus-2025-12-01` …
Moonshot	3	Coding, Text, Video, Vision	`kimi-k2-thinking`, `kimi-k2.5`, `kimi-k2.6`
MiniMax	2	Coding, Text, Video, Vision	`MiniMax-M2.5`, `MiniMax-M3`
Zhipu GLM	1	Coding, Text	`glm-5`
ByteDance	8	Text, Video, Vision, Coding, Image	`seed-1-6-250915`, `seed-1-6-flash-250715`, `seed-1-8-251228`, `seed-2-0-lite-260228` …

完整模型详情

OpenAI

模型 ID	上下文	能力	Endpoint	计费
`gpt-5`	400,000	Coding, Text, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$1.2500 in /$ 10.0000 out per 1M tokens (cache read $0.1250/M)
`gpt-5-mini`	400,000	Coding, Text, Vision; reasoning, long context, creative writing, spatial vision, document vision, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.1500 in /$ 1.2000 out per 1M tokens (cache read $0.0150/M)
`gpt-5.2`	400,000	Coding, Text, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$1.7500 in /$ 14.0000 out per 1M tokens (cache read $1.7500/M)
`gpt-5.2-chat-latest`	400,000	Coding, Text, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$1.7500 in /$ 14.0000 out per 1M tokens (cache read $1.7500/M)
`gpt-5.3-codex`	1,000,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$1.7500 in /$ 14.0000 out per 1M tokens (cache read $1.7500/M)
`gpt-5.4`	1,050,000	Coding, Text, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	`POST /v1/responses`	$2.5000 in /$ 15.0000 out per 1M tokens (cache read $2.5000/M)
`gpt-5.5`	400,000	Coding, Text, Vision; code reasoning, long context, reasoning, vision	`POST /v1/messages`, `POST /v1/chat/completions`, `POST /v1/responses`	$5.0000 in /$ 40.0000 out per 1M tokens (cache read $5.0000/M)
`gpt-image-2`	N/A	Image, Vision; image editing, image generation, text in images, vision	`POST /v1/images/generations`	$8.0000 in /$ 30.0000 out per 1M tokens (cache write $2.0000/M)

Anthropic

模型 ID	上下文	能力	Endpoint	计费
`claude-haiku-4-5-20251001`	200,000	Coding, Text, Vision; reasoning, long context, spatial vision, document vision, visual coding, code reasoning, agentic coding	`POST /v1/messages`, `POST /v1/chat/completions`	$1.0000 in /$ 5.0000 out per 1M tokens (cache read $0.1000/M; cache write$ 2.0000/M)
`claude-opus-4-1-20250805`	200,000	Coding, Text, Vision; reasoning, long context, document vision, visual coding, code reasoning, agentic coding	`POST /v1/messages`, `POST /v1/chat/completions`	$15.0000 in /$ 75.0000 out per 1M tokens (cache read $1.5000/M; cache write$ 30.0000/M)
`claude-opus-4-5-20251101`	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, document vision, visual coding, code reasoning, code completion, agentic coding	`POST /v1/messages`, `POST /v1/chat/completions`	$5.0000 in /$ 25.0000 out per 1M tokens (cache read $0.5000/M; cache write$ 10.0000/M)
`claude-opus-4-6`	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, document vision, visual coding, code reasoning, code completion, agentic coding	`POST /v1/messages`, `POST /v1/chat/completions`	$5.0000 in /$ 25.0000 out per 1M tokens (cache read $0.5000/M; cache write$ 10.0000/M)
`claude-opus-4-7`	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	`POST /v1/messages`, `POST /v1/chat/completions`	$5.0000 in /$ 25.0000 out per 1M tokens (cache read $0.5000/M; cache write$ 10.0000/M)
`claude-opus-4-8`	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	`POST /v1/messages`, `POST /v1/chat/completions`	$5.0000 in /$ 25.0000 out per 1M tokens (cache read $0.5000/M; cache write$ 10.0000/M)
`claude-sonnet-4-5-20250929`	200,000	Coding, Text, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	`POST /v1/messages`, `POST /v1/chat/completions`	$3.0000 in /$ 15.0000 out per 1M tokens (cache read $0.3000/M; cache write$ 6.0000/M)

Google Gemini

模型 ID	上下文	能力	Endpoint	计费
`gemini-3-pro-preview`	N/A	Text; long context, creative writing	`POST /v1/chat/completions`	$2.0000 in /$ 12.0000 out per 1M tokens
`gemini-3.5-flash`	N/A	Text; long context, creative writing	`POST /v1beta/models/{model}:generateContent`, `POST /v1/chat/completions`	$1.5000 in /$ 9.0000 out per 1M tokens (cache read $0.1500/M)

xAI

模型 ID	上下文	能力	Endpoint	计费
`grok-4.20-0309-non-reasoning`	1,000,000	Text, Vision; long context, creative writing, spatial vision, document vision	`POST /v1/chat/completions`	$1.2500 in /$ 2.5000 out per 1M tokens
`grok-4.20-0309-reasoning`	1,000,000	Text, Vision; reasoning, long context, creative writing, spatial vision, document vision	`POST /v1/chat/completions`	$1.2500 in /$ 2.5000 out per 1M tokens
`grok-4.3`	1,000,000	Text, Vision; reasoning, long context, creative writing, spatial vision, document vision	`POST /v1/chat/completions`	$1.2500 in /$ 2.5000 out per 1M tokens
`grok-build-0.1`	256,000	Coding, Text, Vision; reasoning, long context, visual coding, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$1.0000 in /$ 2.0000 out per 1M tokens

DeepSeek

模型 ID	上下文	能力	Endpoint	计费
`deepseek-r1`	262,144	Coding, Text; code reasoning, long context, reasoning	`POST /v1/chat/completions`	$0.4018 in /$ 1.6058 out per 1M tokens (cache read $0.4018/M)
`deepseek-v3`	262,144	Coding, Text; code reasoning, long context, reasoning	`POST /v1/chat/completions`	$0.2009 in /$ 0.8029 out per 1M tokens (cache read $0.2009/M)
`deepseek-v3.1`	262,144	Coding, Text; code reasoning, long context, reasoning	`POST /v1/chat/completions`	$0.4018 in /$ 1.2047 out per 1M tokens (cache read $0.4018/M)
`deepseek-v3.2`	128,000	Coding, Text; reasoning, long context, creative writing, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.2009 in /$ 0.3017 out per 1M tokens (cache read $0.2009/M)
`deepseek-v4-flash`	262,144	Coding, Text; code reasoning, long context, reasoning	`POST /v1/chat/completions`	$0.0980 in /$ 0.1960 out per 1M tokens (cache read $0.0020/M)
`deepseek-v4-pro`	262,144	Coding, Text; code reasoning, long context, reasoning	`POST /v1/messages`, `POST /v1/chat/completions`, `POST /v1/responses`	$0.3045 in /$ 0.6090 out per 1M tokens (cache read $0.0025/M)

Alibaba

模型 ID	上下文	能力	Endpoint	计费
`qwen-flash`	1,000,000	Audio, Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, speech-to-speech, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.0225 in /$ 0.1800 out per 1M tokens (cache read $0.0225/M)
`qwen-mt-flash`	1,000,000	Text; long context, translation	`POST /v1/chat/completions`	$0.0720 in /$ 0.2205 out per 1M tokens (cache read $0.0720/M)
`qwen-mt-lite`	1,000,000	Text; translation	`POST /v1/chat/completions`	$0.0840 in /$ 0.2520 out per 1M tokens (cache read $0.0840/M)
`qwen-plus-2025-12-01`	1,000,000	Audio, Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, speech-to-speech, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.2800 in /$ 0.8400 out per 1M tokens (cache read $0.2800/M)
`qwen3-coder-480b-a35b-instruct`	262,144	Coding, Text; reasoning, long context, code reasoning, agentic coding	`POST /v1/chat/completions`	$1.0500 in /$ 5.2500 out per 1M tokens (cache read $1.0500/M)
`qwen3-coder-flash`	1,000,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.2100 in /$ 1.0500 out per 1M tokens (cache read $0.2100/M)
`qwen3-coder-plus`	1,000,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.7000 in /$ 3.5000 out per 1M tokens (cache read $0.7000/M)
`qwen3-max`	262,144	Audio, Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, speech-to-speech, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.7200 in /$ 3.6000 out per 1M tokens (cache read $0.7200/M)
`qwen3-vl-flash`	131,072	Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.0350 in /$ 0.2800 out per 1M tokens (cache read $0.0350/M)
`qwen3-vl-flash-2025-10-15`	131,072	Coding, Text, Video, Vision; reasoning, long context, translation, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.0350 in /$ 0.2800 out per 1M tokens (cache read $0.0350/M)
`qwen3-vl-plus`	131,072	Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.1400 in /$ 1.1200 out per 1M tokens (cache read $0.1400/M)
`qwen3.6-plus`	1,000,000	Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, omni/video understanding, long video, temporal video, code reasoning, agentic coding	`POST /v1/chat/completions`	$0.2760 in /$ 1.6510 out per 1M tokens (cache read $0.2760/M)
`qwen3.6-plus-2026-04-02`	262,144	Coding, Text, Vision; code reasoning, long context, reasoning, vision	`POST /v1/chat/completions`	$0.2760 in /$ 1.6510 out per 1M tokens (cache read $0.2760/M)
`qwen3.7-max`	1,000,000	Coding, Text; reasoning, long context, translation, creative writing, code reasoning, agentic coding	`POST /v1/chat/completions`	$1.1550 in /$ 3.4657 out per 1M tokens (cache read $0.1155/M; cache write$ 1.4441/M)
`wan2.7-image`	N/A	Image, Text, Vision; reasoning, vision, image generation, image editing, text in images, image consistency	`POST /v1/chat/completions`	$0.030 / request
`wan2.7-image-pro`	N/A	Image, Text, Video, Vision; reasoning, long context, vision, image generation, image editing, text in images, image consistency, image-to-video	`POST /v1/chat/completions`	$0.075 / request

Moonshot

模型 ID	上下文	能力	Endpoint	计费
`kimi-k2-thinking`	256,000	Coding, Text; reasoning, long context, code reasoning, agentic coding	`POST /v1/chat/completions`	$0.4018 in /$ 1.6058 out per 1M tokens (cache read $0.4018/M)
`kimi-k2.5`	262,144	Coding, Text, Video, Vision; reasoning, long context, spatial vision, document vision, visual coding, omni/video understanding, long video, code reasoning, agentic coding	`POST /v1/chat/completions`	$0.4018 in /$ 2.1077 out per 1M tokens (cache read $0.4018/M)
`kimi-k2.6`	128,000	Text; long context, reasoning	`POST /v1/chat/completions`	$0.6257 in /$ 2.5992 out per 1M tokens (cache read $0.6257/M)

MiniMax

模型 ID	上下文	能力	Endpoint	计费
`MiniMax-M2.5`	262,144	Coding, Text; reasoning, long context, creative writing, code reasoning, agentic coding	`POST /v1/chat/completions`	$0.2100 in /$ 0.8400 out per 1M tokens (cache read $0.2100/M)
`MiniMax-M3`	1,000,000	Coding, Text, Video, Vision; reasoning, long context, code reasoning, agentic coding, vision, long video	`POST /v1/messages`, `POST /v1/chat/completions`, `POST /v1/responses`	$0.2100 in /$ 0.8400 out per 1M tokens (cache read $0.0500/M)

Zhipu GLM

模型 ID	上下文	能力	Endpoint	计费
`glm-5`	128,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.4011 in /$ 1.8060 out per 1M tokens (cache read $0.4011/M)

ByteDance

模型 ID	上下文	能力	Endpoint	计费
`seed-1-6-250915`	262,144	Text, Video, Vision; reasoning, long context, creative writing, vision, omni/video understanding	`POST /v1/chat/completions`	$0.2250 in /$ 0.9000 out per 1M tokens (cache read $0.2250/M)
`seed-1-6-flash-250715`	262,144	Text, Video, Vision; reasoning, long context, spatial vision, omni/video understanding, temporal video	`POST /v1/chat/completions`	$0.0675 in /$ 0.2700 out per 1M tokens (cache read $0.0675/M)
`seed-1-8-251228`	262,144	Coding, Text, Video, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.2250 in /$ 1.8000 out per 1M tokens (cache read $0.2250/M)
`seed-2-0-lite-260228`	262,144	Coding, Text, Video, Vision; reasoning, long context, creative writing, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.2500 in /$ 2.0000 out per 1M tokens (cache read $0.2500/M)
`seed-2-0-mini-260215`	262,144	Coding, Text, Video, Vision; reasoning, long context, spatial vision, document vision, omni/video understanding, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.1000 in /$ 0.4000 out per 1M tokens (cache read $0.1000/M)
`seed-2-0-pro-260328`	262,144	Coding, Text, Video, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	`POST /v1/chat/completions`	$0.5000 in /$ 3.0000 out per 1M tokens (cache read $0.5000/M)
`seedream-4-5-251128`	N/A	Image, Vision; vision, image generation, image editing, text in images, image consistency	`POST /v1/chat/completions`	$0.036 / request
`seedream-5-0-260128`	262,144	Image, Vision; image editing, image generation, text in images, vision	`POST /v1/chat/completions`	$0.035 / request

如何选择模型

需求	可优先尝试	原因
前沿文本 + 视觉	`gpt-5.5`, `claude-opus-4-8`, `gpt-5.4`	推理能力强，多模态和代码能力覆盖广。
Agent 编程	`gpt-5.3-codex`, `claude-opus-4-8`, `qwen3-coder-plus`, `MiniMax-M3`	具备代码、长上下文和 Agent 子能力。
低成本高频文本任务	`qwen-flash`, `deepseek-v4-flash`, `qwen-mt-flash`	常规任务的输入/输出价格较低。
长上下文中文或双语任务	`qwen3.6-plus`, `qwen3.7-max`, `MiniMax-M3`	提供 1M token 上下文选项，并具备较强中文能力。
视觉/文档任务	`qwen3-vl-plus`, `claude-opus-4-8`, `gpt-5.4`	带有视觉、文档和空间理解能力标签。
图像生成	`gpt-image-2`, `seedream-5-0-260128`, `wan2.7-image-pro`	支持图像生成和图像编辑，并按请求计费。

Agent 使用注意事项

不要编造 AIsa 模型 ID。请使用表格中的精确 model 字符串。
不要假设某个模型支持其上游模型族的所有模态。请以这里列出的能力标签为准，或查看实时模型页面。
如果某个模型出现在 aisa.one/models 但未出现在静态表格中，可能是定价 API 已在运行时启用该模型；请优先参考实时目录。
价格表仅供参考。最终计费金额以 AIsa Usage Logs 为准，并可能包含工作区级别的定价规则。

​如何调用模型

​Endpoint 类型

​能力标签说明

​Provider 概览

​完整模型详情

​OpenAI

​Anthropic

​Google Gemini

​xAI

​DeepSeek

​Alibaba

​Moonshot

​MiniMax

​Zhipu GLM

​ByteDance

​如何选择模型

​Agent 使用注意事项