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 |
|---|---|
POST /v1/chat/completions | 95 |
POST /v1/messages | 85 |
POST /v1/responses | 72 |
POST /v1/video/generations | 8 |
POST /v1/images/generations | 4 |
POST /v1/images/edits | 3 |
POST /v1/embeddings | 2 |
POST /v1beta/models/{model}:generateContent | 2 |
chat/completions 和 Anthropic 兼容的 messages，因此同一个模型 ID 在两种 SDK 下都能直接用。POST /v1/responses 现已覆盖大多数文本模型 —— 上表只统计 2026 年 8 月 5 日线上网关定价数据报告的路由。在模型不支持的路由上调用会返回 400 model_route_not_supported，并附带该模型支持的路由列表，因此切换协议前请先探测。Gemini 模型额外提供 generateContent。图像模型使用 images/generations 和 images/edits。视频模型是异步任务制：先提交到 POST /v1/video/generations，再轮询 /v1/video/generations/{task_id} 获取结果。Embedding 模型使用 /v1/embeddings。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 |
|---|---|
| 文本 | 自然语言生成、摘要、分析、翻译和长上下文推理。 |
| 编程 | 代码推理、代码补全、软件 Agent 规划和工具调用流程。 |
| 视觉 | 图像/文档理解、视觉编码，以及基于视觉输入的空间推理。 |
| 音频 | 上游模型支持时的音频理解或语音到语音交互。 |
| 图像 | 图像生成、图像编辑、图像一致性，或在图像中渲染文字。 |
| 视频 | 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 | 类型 | 示例模型 ID |
|---|---|---|---|
| OpenAI | 27 | Image, Text | gpt-4.1-mini, gpt-4o, gpt-4o-mini, gpt-5-chat-latest … |
| Anthropic | 12 | Text | claude-fable-5, claude-haiku-4-5-20251001, claude-opus-4-1-20250805, claude-opus-4-5-20251101 … |
| Google Gemini | 2 | Text | gemini-3-pro-preview, gemini-3.5-flash |
| xAI | 5 | Text | grok-4.20-0309-non-reasoning, grok-4.20-0309-reasoning, grok-4.3, grok-4.5 … |
| DeepSeek | 7 | Text | deepseek-r1, deepseek-v3, deepseek-v3.1, deepseek-v3.2 … |
| Alibaba | 24 | Image, Text, Video | qwen-flash, qwen-mt-flash, qwen-mt-lite, qwen-plus-2025-12-01 … |
| Moonshot | 5 | Text | kimi-k2-thinking, kimi-k2.5, kimi-k2.6, kimi-k2.7-code … |
| MiniMax | 2 | Text | MiniMax-M2.5, MiniMax-M3 |
| Zhipu GLM | 4 | Text | glm-5, glm-5.1, glm-5.2 … |
| ByteDance | 10 | Image, Text, Video | seed-1-6-250915, seed-1-6-flash-250715, seed-1-8-251228, seed-2-0-lite-260228 … |
| Xiaomi | 2 | Text | mimo-v2.5, mimo-v2.5-pro |
| StepFun | 3 | Text | step-3.5-flash, step-3.5-flash-2603, step-3.7-flash |
| HappyHorse | 3 | Video | happyhorse-1.1-i2v, happyhorse-1.1-r2v, happyhorse-1.1-t2v |
| 其他 | 2 | Embeddings | text-embedding-3-large, text-embedding-3-small |
完整模型详情
上下文窗口和能力标签来自上一次 Model Gateway 元数据导出。此后新增的模型，上下文列显示—，能力列只标注基础类型 —— 这些模型的实时上下文限制和能力标签请查看 aisa.one/models。
OpenAI
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
gpt-4.1-mini | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.4211 输入 / $1.6842 输出，每 1M Token（缓存读取 $0.1053/M） |
gpt-4o | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $2.6316 输入 / $10.5263 输出，每 1M Token（缓存读取 $1.3158/M） |
gpt-4o-mini | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.1579 输入 / $0.6316 输出，每 1M Token（缓存读取 $0.0789/M） |
gpt-5-chat-latest | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.3158 输入 / $10.5263 输出，每 1M Token（缓存读取 $0.1316/M） |
gpt-5-nano | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.0526 输入 / $0.4211 输出，每 1M Token（缓存读取 $0.0053/M） |
gpt-5-pro | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $15.7895 输入 / $126.3158 输出，每 1M Token |
gpt-5-search-api | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.3158 输入 / $10.5263 输出，每 1M Token（缓存读取 $0.1316/M） |
gpt-5.1 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.3158 输入 / $10.5263 输出，每 1M Token（缓存读取 $0.1316/M） |
gpt-5.1-chat-latest | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.3158 输入 / $10.5263 输出，每 1M Token（缓存读取 $0.1316/M） |
gpt-5.1-codex | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.3158 输入 / $10.5263 输出，每 1M Token（缓存读取 $0.1316/M） |
gpt-5.1-codex-max | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.3158 输入 / $10.5263 输出，每 1M Token（缓存读取 $0.1316/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 | /v1/chat/completions, /v1/messages, /v1/responses | $1.8421 输入 / $14.7368 输出，每 1M Token（缓存读取 $0.1842/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 | /v1/chat/completions, /v1/messages, /v1/responses | $1.8421 输入 / $14.7368 输出，每 1M Token（缓存读取 $0.1842/M） |
gpt-5.2-codex | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.8421 输入 / $14.7368 输出，每 1M Token（缓存读取 $0.1842/M） |
gpt-5.2-pro | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $22.1053 输入 / $176.8421 输出，每 1M Token |
gpt-5.3-chat-latest | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.8421 输入 / $14.7368 输出，每 1M Token（缓存读取 $0.1842/M） |
gpt-5.3-codex | 1,000,000 | Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $1.8421 输入 / $14.7368 输出，每 1M Token（缓存读取 $0.1842/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 | /v1/chat/completions, /v1/messages, /v1/responses | $2.6316 输入 / $15.7895 输出，每 1M Token（缓存读取 $0.2632/M） |
gpt-5.4-mini | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.7895 输入 / $4.7368 输出，每 1M Token（缓存读取 $0.0789/M） |
gpt-5.4-nano | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.2105 输入 / $1.3158 输出，每 1M Token（缓存读取 $0.0211/M） |
gpt-5.4-pro | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $31.5789 输入 / $189.4737 输出，每 1M Token |
gpt-5.5 | 400,000 | Coding, Text, Vision; code reasoning, long context, reasoning, vision | /v1/chat/completions, /v1/messages, /v1/responses | $5.2632 输入 / $40.0000 输出，每 1M Token（缓存读取 $0.5263/M） |
gpt-5.5-pro | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $31.5789 输入 / $189.4737 输出，每 1M Token |
gpt-5.6-luna | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.2105 输入 / $1.2632 输出，每 1M Token（缓存读取 $0.0211/M；缓存写入 $0.2500/M） |
gpt-5.6-sol | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $5.2632 输入 / $31.5789 输出，每 1M Token（缓存读取 $0.5263/M；缓存写入 $6.2500/M） |
gpt-5.6-terra | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $2.1053 输入 / $12.6316 输出，每 1M Token（缓存读取 $0.2105/M；缓存写入 $2.5000/M） |
gpt-image-2 | 不适用 | Image, Vision; image editing, image generation, text in images, vision | /v1/images/generations, /v1/images/edits | $8.4211 输入 / $31.5789 输出，每 1M Token（缓存写入 $2.0000/M）；$0.03 / 次请求; $0.05 / 张图 (1024x1024) |
Anthropic
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
claude-fable-5 | — | Text | /v1/chat/completions, /v1/messages | $10.5263 输入 / $52.6316 输出，每 1M Token（缓存读取 $1.0526/M；缓存写入 $12.5000/M） |
claude-haiku-4-5-20251001 | 200,000 | Coding, Text, Vision; reasoning, long context, spatial vision, document vision, visual coding, code reasoning, agentic coding | /v1/chat/completions, /v1/messages | $1.0526 输入 / $5.2632 输出，每 1M Token（缓存读取 $0.1053/M；缓存写入 $2.0000/M） |
claude-opus-4-1-20250805 | 200,000 | Coding, Text, Vision; reasoning, long context, document vision, visual coding, code reasoning, agentic coding | /v1/chat/completions, /v1/messages | $15.7895 输入 / $78.9474 输出，每 1M Token（缓存读取 $1.5789/M；缓存写入 $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 | /v1/chat/completions, /v1/messages | $5.2632 输入 / $26.3158 输出，每 1M Token（缓存读取 $0.5263/M；缓存写入 $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 | /v1/chat/completions, /v1/messages | $5.2632 输入 / $26.3158 输出，每 1M Token（缓存读取 $0.5263/M；缓存写入 $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 | /v1/chat/completions, /v1/messages, /v1/responses | $5.2632 输入 / $26.3158 输出，每 1M Token（缓存读取 $0.5263/M；缓存写入 $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 | /v1/chat/completions, /v1/messages | $5.2632 输入 / $26.3158 输出，每 1M Token（缓存读取 $0.5263/M；缓存写入 $10.0000/M） |
claude-opus-5 | — | Text | /v1/chat/completions, /v1/messages | $5.2632 输入 / $26.3158 输出，每 1M Token（缓存读取 $0.5263/M；缓存写入 $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 | /v1/chat/completions, /v1/messages | $3.1579 输入 / $15.7895 输出，每 1M Token（缓存读取 $0.3158/M；缓存写入 $6.0000/M） |
claude-sonnet-4-6 | — | Text | /v1/chat/completions, /v1/messages | $3.1579 输入 / $15.7895 输出，每 1M Token（缓存读取 $0.3158/M；缓存写入 $6.0000/M） |
claude-sonnet-4-6-thinking | — | Text | /v1/chat/completions, /v1/messages | $3.1579 输入 / $15.7895 输出，每 1M Token（缓存读取 $0.3158/M；缓存写入 $6.0000/M） |
claude-sonnet-5 | — | Text | /v1/chat/completions, /v1/messages | $2.1053 输入 / $10.5263 输出，每 1M Token（缓存读取 $0.2105/M；缓存写入 $2.5000/M） |
Google Gemini
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
gemini-3-pro-preview | 不适用 | Text; long context, creative writing | /v1/chat/completions, /v1beta/models/{model}:generateContent | $2.1053 输入 / $12.6316 输出，每 1M Token |
gemini-3.5-flash | 不适用 | Text; long context, creative writing | /v1/chat/completions, /v1beta/models/{model}:generateContent | $1.5789 输入 / $9.4737 输出，每 1M Token（缓存读取 $0.1579/M） |
xAI
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
grok-4.20-0309-non-reasoning | 1,000,000 | Text, Vision; long context, creative writing, spatial vision, document vision | /v1/chat/completions | $1.3158 输入 / $2.6316 输出，每 1M Token |
grok-4.20-0309-reasoning | 1,000,000 | Text, Vision; reasoning, long context, creative writing, spatial vision, document vision | /v1/chat/completions | $1.3158 输入 / $2.6316 输出，每 1M Token |
grok-4.3 | 1,000,000 | Text, Vision; reasoning, long context, creative writing, spatial vision, document vision | /v1/chat/completions | $1.3158 输入 / $2.6316 输出，每 1M Token |
grok-4.5 | — | Text | /v1/chat/completions | $2.1053 输入 / $6.3158 输出，每 1M Token（缓存写入 $0.5000/M） |
grok-build-0.1 | 256,000 | Coding, Text, Vision; reasoning, long context, visual coding, code reasoning, code completion, agentic coding | /v1/chat/completions | $1.0526 输入 / $2.1053 输出，每 1M Token |
DeepSeek
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
deepseek-r1 | 262,144 | Coding, Text; code reasoning, long context, reasoning | /v1/chat/completions, /v1/messages, /v1/responses | $0.4229 输入 / $1.6903 输出，每 1M Token（缓存读取 $0.4229/M） |
deepseek-v3 | 262,144 | Coding, Text; code reasoning, long context, reasoning | /v1/chat/completions, /v1/messages, /v1/responses | $0.2115 输入 / $0.8452 输出，每 1M Token（缓存读取 $0.2115/M） |
deepseek-v3.1 | 262,144 | Coding, Text; code reasoning, long context, reasoning | /v1/chat/completions, /v1/messages, /v1/responses | $0.4229 输入 / $1.2681 输出，每 1M Token（缓存读取 $0.4229/M） |
deepseek-v3.2 | 128,000 | Coding, Text; reasoning, long context, creative writing, code reasoning, code completion, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $0.2115 输入 / $0.3176 输出，每 1M Token（缓存读取 $0.2115/M） |
deepseek-v4-flash | 262,144 | Coding, Text; code reasoning, long context, reasoning | /v1/chat/completions, /v1/messages, /v1/responses | $0.1032 输入 / $0.2063 输出，每 1M Token（缓存读取 $0.0021/M） |
deepseek-v4-flash-0731 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.1380 输入 / $0.2750 输出，每 1M Token（缓存写入 $0.0280/M） |
deepseek-v4-pro | 262,144 | Coding, Text; code reasoning, long context, reasoning | /v1/chat/completions, /v1/messages, /v1/responses | $0.3205 输入 / $0.6411 输出，每 1M Token（缓存读取 $0.0027/M） |
Alibaba
| Model ID | 上下文 | 能力 | Endpoint(s) | 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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.0154 输入 / $0.1512 输出，每 1M Token（缓存读取 $0.0035/M） |
qwen-mt-flash | 1,000,000 | Text; long context, translation | /v1/chat/completions, /v1/messages, /v1/responses | $0.0720 输入 / $0.2205 输出，每 1M Token（缓存读取 $0.0720/M） |
qwen-mt-lite | 1,000,000 | Text; translation | /v1/chat/completions, /v1/messages, /v1/responses | $0.0840 输入 / $0.2520 输出，每 1M Token（缓存读取 $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 | /v1/chat/completions | $0.2800 输入 / $0.8400 输出，每 1M Token（缓存读取 $0.2800/M） |
qwen3-coder-480b-a35b-instruct | 262,144 | Coding, Text; reasoning, long context, code reasoning, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $1.0500 输入 / $5.2500 输出，每 1M Token（缓存读取 $1.0500/M） |
qwen3-coder-flash | 1,000,000 | Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $0.2100 输入 / $1.0500 输出，每 1M Token（缓存读取 $0.2100/M） |
qwen3-coder-plus | 1,000,000 | Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $0.7000 输入 / $3.5000 输出，每 1M Token（缓存读取 $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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.7200 输入 / $3.6000 输出，每 1M Token（缓存读取 $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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.0350 输入 / $0.2800 输出，每 1M Token（缓存读取 $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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.0350 输入 / $0.2800 输出，每 1M Token（缓存读取 $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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.1400 输入 / $1.1200 输出，每 1M Token（缓存读取 $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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.2760 输入 / $1.6510 输出，每 1M Token（缓存读取 $0.2760/M） |
qwen3.6-plus-2026-04-02 | 262,144 | Coding, Text, Vision; code reasoning, long context, reasoning, vision | /v1/chat/completions, /v1/messages, /v1/responses | $0.2760 输入 / $1.6510 输出，每 1M Token（缓存读取 $0.2760/M） |
qwen3.7-flash | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.1732 输入 / $0.6930 输出，每 1M Token（缓存读取 $0.0347/M；缓存写入 $0.2166/M） |
qwen3.7-flash-2026-07-15 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.1732 输入 / $0.6930 输出，每 1M Token（缓存读取 $0.0347/M；缓存写入 $0.2166/M） |
qwen3.7-max | 1,000,000 | Coding, Text; reasoning, long context, translation, creative writing, code reasoning, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $1.1550 输入 / $3.4657 输出，每 1M Token（缓存读取 $0.1155/M；缓存写入 $1.4441/M） |
qwen3.7-max-2026-06-08 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.1550 输入 / $3.4657 输出，每 1M Token（缓存读取 $0.2310/M） |
qwen3.7-plus | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.1932 输入 / $0.7707 输出，每 1M Token（缓存读取 $0.0392/M） |
qwen3.8-max | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.7325 输入 / $5.1986 输出，每 1M Token（缓存读取 $0.2163/M；缓存写入 $2.1662/M） |
wan2.7-i2v | — | Video | /v1/video/generations | $0.060208 / 输出秒 (720p); $0.100347 / 输出秒 (1080p) |
wan2.7-image | 不适用 | Image, Text, Vision; reasoning, vision, image generation, image editing, text in images, image consistency | /v1/images/generations, /v1/images/edits | $0.03 / 次请求 |
wan2.7-image-pro | 不适用 | Image, Text, Video, Vision; reasoning, long context, vision, image generation, image editing, text in images, image consistency, image-to-video | /v1/images/generations, /v1/images/edits | $0.075 / 次请求 |
wan2.7-r2v | — | Video | /v1/video/generations | $0.060208 / 输出秒 (720p); $0.100347 / 输出秒 (1080p) |
wan2.7-t2v | — | Video | /v1/video/generations | $0.060208 / 输出秒 (720p); $0.100347 / 输出秒 (1080p) |
Moonshot
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
kimi-k2-thinking | 256,000 | Coding, Text; reasoning, long context, code reasoning, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $0.4229 输入 / $1.6903 输出，每 1M Token（缓存读取 $0.4229/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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.4229 输入 / $2.2186 输出，每 1M Token（缓存读取 $0.0847/M） |
kimi-k2.6 | 128,000 | Text; long context, reasoning | /v1/chat/completions, /v1/messages, /v1/responses | $0.6587 输入 / $2.7360 输出，每 1M Token（缓存读取 $0.6587/M） |
kimi-k2.7-code | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.6257 输入 / $2.5992 输出，每 1M Token（缓存读取 $0.1252/M） |
kimi-k3 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $3.1579 输入 / $15.7895 输出，每 1M Token（缓存读取 $0.3158/M） |
MiniMax
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
MiniMax-M2.5 | 262,144 | Coding, Text; reasoning, long context, creative writing, code reasoning, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $0.2211 输入 / $0.8842 输出，每 1M Token（缓存读取 $0.2211/M） |
MiniMax-M3 | 1,000,000 | Coding, Text, Video, Vision; reasoning, long context, code reasoning, agentic coding, vision, long video | /v1/chat/completions, /v1/messages, /v1/responses | $0.2211 输入 / $0.8842 输出，每 1M Token（缓存读取 $0.0526/M） |
Zhipu GLM
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
glm-5 | 128,000 | Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding | /v1/chat/completions, /v1/messages, /v1/responses | $0.4222 输入 / $1.9011 输出，每 1M Token（缓存读取 $0.4222/M） |
glm-5.1 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.5775 输入 / $2.3107 输出，每 1M Token（缓存读取 $0.1155/M） |
glm-5.2 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.7700 输入 / $2.6957 输出，每 1M Token（缓存读取 $0.1925/M） |
z-ai/glm-5v-turbo | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $1.2000 输入 / $4.0000 输出，每 1M Token（缓存读取 $0.2400/M） |
ByteDance
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
seed-1-6-250915 | 262,144 | Text, Video, Vision; reasoning, long context, creative writing, vision, omni/video understanding | /v1/chat/completions, /v1/messages, /v1/responses | $0.2368 输入 / $0.9474 输出，每 1M Token（缓存读取 $0.2368/M） |
seed-1-6-flash-250715 | 262,144 | Text, Video, Vision; reasoning, long context, spatial vision, omni/video understanding, temporal video | /v1/chat/completions, /v1/messages, /v1/responses | $0.0711 输入 / $0.2842 输出，每 1M Token（缓存读取 $0.0711/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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.2368 输入 / $1.8947 输出，每 1M Token（缓存读取 $0.2368/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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.2632 输入 / $2.1053 输出，每 1M Token（缓存读取 $0.2632/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 | /v1/chat/completions | $0.1053 输入 / $0.4211 输出，每 1M Token（缓存读取 $0.1053/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 | /v1/chat/completions, /v1/messages, /v1/responses | $0.5263 输入 / $3.1579 输出，每 1M Token（缓存读取 $0.5263/M） |
dreamina-seedance-2-0-260128 | — | Video | /v1/video/generations | $4.3 / 1M Token (480p, 720p, 4k); $4.7 / 1M Token (1080p) |
dreamina-seedance-2-0-fast-260128 | — | Video | /v1/video/generations | $3.3 / 1M Token (480p, 720p) |
seedream-4-5-251128 | 不适用 | Image, Vision; vision, image generation, image editing, text in images, image consistency | /v1/chat/completions | $0.036 / 次请求 |
seedream-5-0-260128 | 262,144 | Image, Vision; image editing, image generation, text in images, vision | /v1/images/generations | $0.035 / 次请求 |
Xiaomi
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
mimo-v2.5 | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.1505 输入 / $0.3011 输出，每 1M Token（缓存读取 $0.0031/M） |
mimo-v2.5-pro | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.5158 输入 / $0.9021 输出，每 1M Token（缓存读取 $0.0038/M） |
StepFun
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
step-3.5-flash | — | Text | /v1/chat/completions, /v1/messages | $0.1053 输入 / $0.3158 输出，每 1M Token（缓存读取 $0.0211/M） |
step-3.5-flash-2603 | — | Text | /v1/chat/completions, /v1/messages | $0.1053 输入 / $0.3158 输出，每 1M Token（缓存读取 $0.0211/M） |
step-3.7-flash | — | Text | /v1/chat/completions, /v1/messages, /v1/responses | $0.2105 输入 / $1.2105 输出，每 1M Token（缓存读取 $0.0421/M） |
HappyHorse
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
happyhorse-1.1-i2v | — | Video | /v1/video/generations | $0.098 / 输出秒（720p）；$0.126 / 输出秒（更高档；上游数据把两档都标为 720p） |
happyhorse-1.1-r2v | — | Video | /v1/video/generations | $0.098 / 输出秒 (720p); $0.126 / 输出秒 (1080p) |
happyhorse-1.1-t2v | — | Video | /v1/video/generations | $0.098 / 输出秒 (720p); $0.126 / 输出秒 (1080p) |
其他
| Model ID | 上下文 | 能力 | Endpoint(s) | 计费 |
|---|---|---|---|---|
text-embedding-3-small | — | Embeddings | /v1/embeddings | $0.0211 输入，每 1M Token |
text-embedding-3-large | — | Embeddings | /v1/embeddings | $0.1368 输入，每 1M Token |
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。 |
gpt-5.6-luna、gpt-5.6-sol、gpt-5.6-terra、claude-opus-5、claude-sonnet-5、kimi-k3、kimi-k2.7-code、glm-5.2 和 grok-4.5 —— 还没有反映在这张表里。在把生产流量切到这些模型前，请先查看实时模型目录。
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。
- 上下文列显示
—表示当前元数据导出没有公布该模型的上下文窗口。不要假设一个默认值，请查看实时模型目录。