API
注意：Ollama 的 API 文档正在迁移至 https://docs.ollama.com/api
端点
约定
模型名称
模型名称遵循 model:tag 格式，其中 model 可以包含可选命名空间，例如 example/model。部分示例如 orca-mini:3b-q8_0 和 llama3:70b。标签是可选的，如果未提供则默认为 latest。标签用于标识特定版本。
时长
所有时长均以纳秒为单位返回。
流式响应
部分端点会以 JSON 对象形式流式返回响应。对于这些端点，可以通过提供 {"stream": false} 来禁用流式传输。
生成补全
POST /api/generate针对给定的提示词和提供的模型生成响应。这是一个流式端点，因此会返回一系列响应。最终的响应对象将包含统计信息以及请求中的额外数据。
参数
model：（必填）模型名称prompt：用于生成响应的提示词suffix：模型响应之后的文本images：（可选）base64 编码的图像列表（适用于多模态模型，例如llava）think：（适用于思考模型）模型是否需要在响应前进行思考？可以是布尔值，或思考等级（"low"、"medium"、"high"或"max"）。
高级参数（可选）：
format：返回响应的格式。格式可以是json或 JSON schemaoptions：Modelfile 文档中列出的额外模型参数，例如temperaturesystem：系统消息（会覆盖Modelfile中定义的内容）template：要使用的提示词模板（会覆盖Modelfile中定义的内容）stream：如果设为false，响应将作为单个响应对象返回，而非对象流raw：如果设为true，则不会对提示词应用任何格式化。如果你在 API 请求中指定了完整的模板化提示词，可以选择使用raw参数keep_alive：控制请求完成后模型在内存中保留的时长（默认值：5m）context（已弃用）：之前请求/generate返回的上下文参数，可用于保留简短的对话记忆
实验性图像生成参数（仅适用于图像生成模型）：
WARNING
这些参数处于实验阶段，未来版本中可能会发生变化。
width：生成图像的宽度，单位为像素height：生成图像的高度，单位为像素steps：扩散步数
结构化输出
通过在 format 参数中提供 JSON schema 即可支持结构化输出。模型将生成符合该 schema 的响应。请参阅下方的结构化输出示例。
JSON 模式
通过将 format 参数设置为 json 来启用 JSON 模式。这会将响应结构化为有效的 JSON 对象。请参阅下方的 JSON 模式示例。
IMPORTANT
务必在 prompt 中指示模型使用 JSON 格式。否则，模型可能会生成大量空白内容。
示例
生成请求（流式）
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?"
}'响应
将返回 JSON 对象流：
json
{
"model": "llama3.2",
"created_at": "2023-08-04T08:52:19.385406455-07:00",
"response": "The",
"done": false
}流中的最终响应还会包含生成相关的额外数据：
total_duration：生成响应所花费的时间load_duration：加载模型所花费的纳秒级时长prompt_eval_count：提示词中的 token 数量prompt_eval_duration：评估提示词所花费的纳秒级时长eval_count：响应中的 token 数量eval_duration：生成响应所花费的纳秒级时长context：本次响应中使用的对话编码，可在下一次请求中发送以保留对话记忆response：如果响应是流式返回的，则为空；如果不是流式返回，则包含完整响应
要计算生成速度（单位：token/秒），请计算 eval_count / eval_duration * 10^9。
json
{
"model": "llama3.2",
"created_at": "2023-08-04T19:22:45.499127Z",
"response": "",
"done": true,
"context": [1, 2, 3],
"total_duration": 10706818083,
"load_duration": 6338219291,
"prompt_eval_count": 26,
"prompt_eval_duration": 130079000,
"eval_count": 259,
"eval_duration": 4232710000
}请求（无流式传输）
请求
关闭流式传输时，可以在一次回复中接收响应。
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"stream": false
}'响应
如果 stream 设为 false，响应将是单个 JSON 对象：
json
{
"model": "llama3.2",
"created_at": "2023-08-04T19:22:45.499127Z",
"response": "The sky is blue because it is the color of the sky.",
"done": true,
"context": [1, 2, 3],
"total_duration": 5043500667,
"load_duration": 5025959,
"prompt_eval_count": 26,
"prompt_eval_duration": 325953000,
"eval_count": 290,
"eval_duration": 4709213000
}请求（带后缀）
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "codellama:code",
"prompt": "def compute_gcd(a, b):",
"suffix": " return result",
"options": {
"temperature": 0
},
"stream": false
}'响应
json5
{
"model": "codellama:code",
"created_at": "2024-07-22T20:47:51.147561Z",
"response": "\n if a == 0:\n return b\n else:\n return compute_gcd(b % a, a)\n\ndef compute_lcm(a, b):\n result = (a * b) / compute_gcd(a, b)\n",
"done": true,
"done_reason": "stop",
"context": [...],
"total_duration": 1162761250,
"load_duration": 6683708,
"prompt_eval_count": 17,
"prompt_eval_duration": 201222000,
"eval_count": 63,
"eval_duration": 953997000
}请求（结构化输出）
请求
shell
curl -X POST http://localhost:11434/api/generate -H "Content-Type: application/json" -d '{
"model": "llama3.1:8b",
"prompt": "Ollama is 22 years old and is busy saving the world. Respond using JSON",
"stream": false,
"format": {
"type": "object",
"properties": {
"age": {
"type": "integer"
},
"available": {
"type": "boolean"
}
},
"required": [
"age",
"available"
]
}
}'响应
json
{
"model": "llama3.1:8b",
"created_at": "2024-12-06T00:48:09.983619Z",
"response": "{\n \"age\": 22,\n \"available\": true\n}",
"done": true,
"done_reason": "stop",
"context": [1, 2, 3],
"total_duration": 1075509083,
"load_duration": 567678166,
"prompt_eval_count": 28,
"prompt_eval_duration": 236000000,
"eval_count": 16,
"eval_duration": 269000000
}请求（JSON 模式）
IMPORTANT
当 format 设为 json 时，输出将始终是格式良好的 JSON 对象。务必同时指示模型以 JSON 格式响应。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "What color is the sky at different times of the day? Respond using JSON",
"format": "json",
"stream": false
}'响应
json
{
"model": "llama3.2",
"created_at": "2023-11-09T21:07:55.186497Z",
"response": "{\n\"morning\": {\n\"color\": \"blue\"\n},\n\"noon\": {\n\"color\": \"blue-gray\"\n},\n\"afternoon\": {\n\"color\": \"warm gray\"\n},\n\"evening\": {\n\"color\": \"orange\"\n}\n}\n",
"done": true,
"context": [1, 2, 3],
"total_duration": 4648158584,
"load_duration": 4071084,
"prompt_eval_count": 36,
"prompt_eval_duration": 439038000,
"eval_count": 180,
"eval_duration": 4196918000
}response 的值将是包含 JSON 的字符串，类似如下：
json
{
"morning": {
"color": "blue"
},
"noon": {
"color": "blue-gray"
},
"afternoon": {
"color": "warm gray"
},
"evening": {
"color": "orange"
}
}请求（带图像）
要向 llava 或 bakllava 等多模态模型提交图像，请提供 base64 编码的 images 列表：
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llava",
"prompt":"What is in this picture?",
"stream": false,
"images": ["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"]
}'响应
json
{
"model": "llava",
"created_at": "2023-11-03T15:36:02.583064Z",
"response": "A happy cartoon character, which is cute and cheerful.",
"done": true,
"context": [1, 2, 3],
"total_duration": 2938432250,
"load_duration": 2559292,
"prompt_eval_count": 1,
"prompt_eval_duration": 2195557000,
"eval_count": 44,
"eval_duration": 736432000
}请求（原始模式）
某些情况下，你可能希望绕过模板系统并提供完整的提示词。此时可以使用 raw 参数禁用模板化。另请注意，原始模式不会返回上下文。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "[INST] why is the sky blue? [/INST]",
"raw": true,
"stream": false
}'请求（可复现输出）
要获得可复现的输出，将 seed 设置为一个数值：
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "Why is the sky blue?",
"options": {
"seed": 123
}
}'响应
json
{
"model": "mistral",
"created_at": "2023-11-03T15:36:02.583064Z",
"response": " The sky appears blue because of a phenomenon called Rayleigh scattering.",
"done": true,
"total_duration": 8493852375,
"load_duration": 6589624375,
"prompt_eval_count": 14,
"prompt_eval_duration": 119039000,
"eval_count": 110,
"eval_duration": 1779061000
}生成请求（带参数）
如果要在运行时而非 Modelfile 中为模型设置自定义参数，可以使用 options 参数。本示例设置了所有可用参数，你也可以单独设置其中任意参数，并省略不需要覆盖的参数。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"stream": false,
"options": {
"num_keep": 5,
"seed": 42,
"num_predict": 100,
"draft_num_predict": 4,
"top_k": 20,
"top_p": 0.9,
"min_p": 0.0,
"typical_p": 0.7,
"repeat_last_n": 33,
"temperature": 0.8,
"repeat_penalty": 1.2,
"presence_penalty": 1.5,
"frequency_penalty": 1.0,
"penalize_newline": true,
"stop": ["\n", "user:"],
"numa": false,
"num_ctx": 1024,
"num_batch": 2,
"num_gpu": 1,
"main_gpu": 0,
"use_mmap": true,
"num_thread": 8
}
}'响应
json
{
"model": "llama3.2",
"created_at": "2023-08-04T19:22:45.499127Z",
"response": "The sky is blue because it is the color of the sky.",
"done": true,
"context": [1, 2, 3],
"total_duration": 4935886791,
"load_duration": 534986708,
"prompt_eval_count": 26,
"prompt_eval_duration": 107345000,
"eval_count": 237,
"eval_duration": 4289432000
}加载模型
如果提供空的提示词，模型将被加载到内存中。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2"
}'响应
将返回单个 JSON 对象：
json
{
"model": "llama3.2",
"created_at": "2023-12-18T19:52:07.071755Z",
"response": "",
"done": true
}卸载模型
如果提供空的提示词且 keep_alive 参数设为 0，模型将从内存中卸载。
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"keep_alive": 0
}'响应
将返回单个 JSON 对象：
json
{
"model": "llama3.2",
"created_at": "2024-09-12T03:54:03.516566Z",
"response": "",
"done": true,
"done_reason": "unload"
}生成聊天补全
POST /api/chat使用指定模型生成聊天中的下一条消息。这是一个流式端点，因此会返回一系列响应。可以通过设置 "stream": false 来禁用流式传输。最终的响应对象将包含统计信息以及请求中的额外数据。
参数
model：（必填）模型名称messages：聊天消息列表，可用于保存聊天记忆tools：JSON 格式的工具列表，模型可在支持的情况下使用这些工具think：（适用于思考型模型）模型是否需要在回复前进行思考？可以是布尔值，也可以是思考等级（"low"、"medium"、"high"或"max"）。
message 对象包含以下字段：
role：消息的角色，可选值为system、user、assistant或toolcontent：消息内容thinking：（适用于思考型模型）模型的思考过程images（可选）：要包含在消息中的图片列表（适用于llava等多模态模型）tool_calls（可选）：模型希望使用的 JSON 格式工具列表tool_name（可选）：已执行工具的名称，用于告知模型执行结果
高级参数（可选）：
format：响应的返回格式，可选值为json或 JSON Schemaoptions：额外模型参数，具体可参考 Modelfile 文档中的说明，例如temperaturestream：如果设置为false，响应将作为单个响应对象返回，而非对象流keep_alive：控制请求完成后模型在内存中保留的时长（默认值：5m）
工具调用
通过在 tools 参数中提供工具列表即可启用工具调用功能。模型会生成包含工具调用列表的响应。请参阅下方的 聊天请求（流式传输，带工具） 示例。模型还可以在响应中解释工具调用的结果。请参阅下方的 聊天请求（带历史记录，带工具） 示例。查看支持工具调用能力的模型。
结构化输出
通过在 format 参数中提供 JSON Schema 即可支持结构化输出。模型会生成符合该 Schema 的响应。请参阅下方的 聊天请求（结构化输出） 示例。
示例
聊天请求（流式传输）
请求
发送带流式响应的聊天消息。
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "why is the sky blue? "
}
]
}'响应
将返回 JSON 对象流：
json
{
"model": "llama3. 2",
"created_at": "2023-08-04T08:52:19. 385406455-07:00",
"message": {
"role": "assistant",
"content": "The",
"images": null
},
"done": false
}最终响应：
json
{
"model": "llama3. 2",
"created_at": "2023-08-04T19:22:45. 499127Z",
"message": {
"role": "assistant",
"content": ""
},
"done": true,
"total_duration": 4883583458,
"load_duration": 1334875,
"prompt_eval_count": 26,
"prompt_eval_duration": 342546000,
"eval_count": 282,
"eval_duration": 4535599000
}聊天请求（流式传输，带工具）
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "what is the weather in tokyo? "
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city to get the weather for"
}
},
"required": ["city"]
}
}
}
],
"stream": true
}'响应
将返回 JSON 对象流：
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:22:19. 184789Z",
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_weather",
"arguments": {
"city": "Tokyo"
}
}
}
]
},
"done": false
}最终响应：
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:22:19. 19314Z",
"message": {
"role": "assistant",
"content": ""
},
"done_reason": "stop",
"done": true,
"total_duration": 182242375,
"load_duration": 41295167,
"prompt_eval_count": 169,
"prompt_eval_duration": 24573166,
"eval_count": 15,
"eval_duration": 115959084
}聊天请求（无流式传输）
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "why is the sky blue? "
}
],
"stream": false
}'响应
json
{
"model": "llama3. 2",
"created_at": "2023-12-12T14:13:43. 416799Z",
"message": {
"role": "assistant",
"content": "Hello! How are you today? "
},
"done": true,
"total_duration": 5191566416,
"load_duration": 2154458,
"prompt_eval_count": 26,
"prompt_eval_duration": 383809000,
"eval_count": 298,
"eval_duration": 4799921000
}聊天请求（无流式传输，带工具）
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "what is the weather in tokyo? "
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city to get the weather for"
}
},
"required": ["city"]
}
}
}
],
"stream": false
}'响应
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:32:53. 844124Z",
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_weather",
"arguments": {
"city": "Tokyo"
}
}
}
]
},
"done_reason": "stop",
"done": true,
"total_duration": 3244883583,
"load_duration": 2969184542,
"prompt_eval_count": 169,
"prompt_eval_duration": 141656333,
"eval_count": 18,
"eval_duration": 133293625
}聊天请求（结构化输出）
请求
shell
curl -X POST http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{
"model": "llama3. 1",
"messages": [{"role": "user", "content": "Ollama is 22 years old and busy saving the world. Return a JSON object with the age and availability. "}],
"stream": false,
"format": {
"type": "object",
"properties": {
"age": {
"type": "integer"
},
"available": {
"type": "boolean"
}
},
"required": [
"age",
"available"
]
},
"options": {
"temperature": 0
}
}'响应
json
{
"model": "llama3. 1",
"created_at": "2024-12-06T00:46:58. 265747Z",
"message": {
"role": "assistant",
"content": "{\"age\": 22, \"available\": false}"
},
"done_reason": "stop",
"done": true,
"total_duration": 2254970291,
"load_duration": 574751416,
"prompt_eval_count": 34,
"prompt_eval_duration": 1502000000,
"eval_count": 12,
"eval_duration": 175000000
}聊天请求（带历史记录）
发送带对话历史记录的聊天消息。你可以使用相同的方法，通过多轮提示或思维链提示来开启对话。
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "why is the sky blue? "
},
{
"role": "assistant",
"content": "due to rayleigh scattering. "
},
{
"role": "user",
"content": "how is that different than mie scattering? "
}
]
}'响应
将返回 JSON 对象流：
json
{
"model": "llama3. 2",
"created_at": "2023-08-04T08:52:19. 385406455-07:00",
"message": {
"role": "assistant",
"content": "The"
},
"done": false
}最终响应：
json
{
"model": "llama3. 2",
"created_at": "2023-08-04T19:22:45. 499127Z",
"done": true,
"total_duration": 8113331500,
"load_duration": 6396458,
"prompt_eval_count": 61,
"prompt_eval_duration": 398801000,
"eval_count": 468,
"eval_duration": 7701267000
}聊天请求（带历史记录，带工具）
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "what is the weather in Toronto? "
},
// 模型返回的消息，追加到历史记录中
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_weather",
"arguments": {
"city": "Toronto"
}
}
}
]
},
// 工具调用结果，追加到历史记录中
{
"role": "tool",
"content": "11 degrees celsius",
"tool_name": "get_weather"
}
],
"stream": false,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city to get the weather for"
}
},
"required": ["city"]
}
}
}
]
}'响应
json
{
"model": "llama3. 2",
"created_at": "2025-07-07T20:43:37. 688511Z",
"message": {
"role": "assistant",
"content": "The current temperature in Toronto is 11°C. "
},
"done_reason": "stop",
"done": true,
"total_duration": 890771750,
"load_duration": 707634750,
"prompt_eval_count": 94,
"prompt_eval_duration": 91703208,
"eval_count": 11,
"eval_duration": 90282125
}聊天请求（带图片）
请求
发送带图片的聊天消息。图片需以数组形式提供，单张图片需采用 Base64 编码。
shell
curl http://localhost:11434/api/chat -d '{
"model": "llava",
"messages": [
{
"role": "user",
"content": "what is in this image?
",
"images": ["iVBORw0KGgoAAAANSUhEUgAAAG0AAABmCAYAAADBPx+VAAAACXBIWXMAAAsTAAALEwEAmpwYAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAA3VSURBVHgB7Z27r0zdG8fX743i1bi1ikMoFMQloXRpKFFIqI7LH4BEQ+NWIkjQuSWCRIEoULk0gsK1kCBI0IhrQVT7tz/7zZo888yz1r7MnDl7z5xvsjkzs2fP3uu71nNfa7lkAsm7d++Sffv2JbNmzUqcc8m0adOSzZs3Z+/XES4ZckAWJEGWPiCxjsQNLWmQsWjRIpMseaxcuTKpG/7HP27I8P79e7dq1ars/yL4/v27S0ejqwv+cUOGEGGpKHR37tzJCEpHV9tnT58+dXXCJDdECBE2Ojrqjh071hpNECjx4cMHVycM1Uhbv359B2F79+51506daxN/+pyRkRFXKyRDAqxEp4yMlDDzXG1NPnnyJKkThoK0VFd1ELZu3TrzXKxKfW7dMBQ6bcuWLW2v0VlHjx41z717927ba22U9APcw7Nnz1oGEPeL3m3p2mTAYYnFmMOMXybPPXv2bNIPpFZr1NHn4HMw0KRBjg9NuRw95s8PEcz/6DZELQd/09C9QGq5RsmSRybqkwHGjh07OsJSsYYm3ijPpyHzoiacg35MLdDSIS/O1yM778jOTwYUkKNHWUzUWaOsylE00MyI0fcnOwIdjvtNdW/HZwNLGg+sR1kMepSNJXmIwxBZiG8tDTpEZzKg0GItNsosY8USkxDhD0Rinuiko2gfL/RbiD2LZAjU9zKQJj8RDR0vJBR1/Phx9+PHj9Z7REF4nTZkxzX4LCXHrV271qXkBAPGfP/atWvu/PnzHe4C97F48eIsRLZ9+3a3f/9+87dwP1JxaF7/3r17ba+5l4EcaVo0lj3SBq5kGTJSQmLWMjgYNei2GPT1MuMqGTDEFHzeQSP2wi/jGnkmPJ/nhccs44jvDAxpVcxnq0F6eT8h4ni/iIWpR5lPyA6ETkNXoSukvpJAD3AsXLiwpZs49+fPn5ke4j10TqYvegSfn0OnafC+Tv9ooA/JPkgQysqQNBzagXY55nO/oa1F7qvIPWkRL12WRpMWUvpVDYmxAPehxWSe8ZEXL20sadYIozfmNch4QJPAfeJgW3rNsnzphBKNJM2KKODo1rVOMRYik5ETy3ix4qWNI81qAAirizgMIc+yhTytx0JWZuNI03qsrgWlGtwjoS9XwgUhWGyhUaRZZQNNIEwCiXD16tXcAHUs79co0vSD8rrJCIW98pzvxpAWyyo3HYwqS0+H0BjStClcZJT5coMm6D2LOF8TolGJtK9fvyZpyiC5ePFi9nc/oJU4eiEP0jVoAnHa9wyJycITMP78+eMeP37sXrx44d6+fdt6f82aNdkx1pg9e3Zb5W+RSRE+n+VjksQWifvVaTKFhn5O8my63K8Qabdv33b379/PiAP//vuvW7BggZszZ072/+TJk91YgkafPn166zXB1rQHFvouAWHq9z3SEevSUerqCn2/dDCeta2jxYbr69evk4MHDyY7d+7MjhMnTiTPnz9Pfv/+nfQT2ggpO2dMF8cghuoM7Ygj5iWCqRlGFml0QC/ftGmTmzt3rmsaKDsgBSPh0/8yPeLLBihLkOKJc0jp8H8vUzcxIA1k6QJ/c78tWEyj5P3o4u9+jywNPdJi5rAH9x0KHcl4Hg570eQp3+vHXGyrmEeigzQsQsjavXt38ujRo44LQuDDhw+TW7duRS1HGgMxhNXHgflaNTOsHyKvHK5Ijo2jbFjJBQK9YwFd6RVMzfgRBmEfP37suBBm/p49e1qjEP2mwTViNRo0VJWH1deMXcNK08uUjVUu7s/zRaL+oLNxz1bpANco4npUgX4G2eFbpDFyQoQxojBCpEGSytmOH8qrH5Q9vuzD6ofQylkCUmh8DBAr+q8JCyVNtWQIidKQE9wNtLSQnS4jDSsxNHogzFuQBw4cyM61UKVsjfr3ooBkPSqqQHesUPWVtzi9/vQi1T+rJj7WiTz4Pt/l3LxUkr5P2VYZaZ4URpsE+st/dujQoaBBYokbrz/8TJNQYLSonrPS9kUaSkPeZyj1AWSj+d+VBoy1pIWVNed8P0Ll/ee5HdGRhrHhR5GGN0r4LGZBaj8oFDJitBTJzIZgFcmU0Y8ytWMZMzJOaXUSrUs5RxKnrxmbb5YXO9VGUhtpXldhEUogFr3IzIsvlpmdosVcGVGXFWp2oU9kLFL3dEkSz6NHEY1sjSRdIuDFWEhd8KxFqsRi1uM/nz9/zpxnwlESONdg6dKlbsaMGS4EHFHtjFIDHwKOo46l4TxSuxgDzi+rE2jg+BaFruOX4HXa0Nnf1lwAPufZeF8/r6zD97WK2qFnGjBxTw5qNGPxT+5T/r7/7RawFC3j4vTp09koCxkeHjqbHJqArmH5UrFKKksnxrK7FuRIs8STfBZv+luugXZ2pR/pP9Ois4z+TiMzUUkUjD0iEi1fzX8GmXyuxUBRcaUfykV0YZnlJGKQpOiGB76x5GeWkWWJc3mOrK6S7xdND+W5N6XyaRgtWJFe13GkaZnKOsYqGdOVVVbGupsyA/l7emTLHi7vwTdirNEt0qxnzAvBFcnQF16xh/TMpUuXHDowhlA9vQVraQhkudRdzOnK+04ZSP3DUhVSP61YsaLtd/ks7ZgtPcXqPqEafHkdqa84X6aCeL7YWlv6edGFHb+ZFICPlljHhg0bKuk0CSvVznWsotRu433alNdFrqG45ejoaPCaUkWERpLXjzFL2Rpllp7PJU2a/v7Ab8N05/9t27Z16KUqoFGsxnI9EosS2niSYg9SpU6B4JgTrvVW1flt1sT+0ADIJU2maXzcUTraGCRaL1Wp9rUMk16PMom8QhruxzvZIegJjFU7LLCePfS8uaQdPny4jTTL0dbee5mYokQsXTIWNY46kuMbnt8Kmec+LGWtOVIl9cT1rCB0V8WqkjAsRwta93TbwNYoGKsUSChN44lgBNCoHLHzquYKrU6qZ8lolCIN0Rh6cP0Q3U6I6IXILYOQI513hJaSKAorFpuHXJNfVlpRtmYBk1Su1obZr5dnKAO+L10Hrj3WZW+E3qh6IszE37F6EB+68mGpvKm4eb9bFrlzrok7fvr0Kfv727dvWRmdVTJHw0qiiCUSZ6wCK+7XL/AcsgNyL74DQQ730sv78Su7+t/A36MdY0sW5o40ahslXr58aZ5HtZB8GH64m9EmMZ7FpYw4T6QnrZfgenrhFxaSiSGXtPnz57e9TkNZLvTjeqhr734CNtrK41L40sUQckmj1lGKQ0rC37x544r8eNXRpnVE3ZZY7zXo8NomiO0ZUCj2uHz58rbXoZ6gc0uA+F6ZeKS/jhRDUq8MKrTho9fEkihMmhxtBI1DxKFY9XLpVcSkfoi8JGnToZO5sU5aiDQIW716ddt7ZLYtMQlhECdBGXZZMWldY5BHm5xgAroWj4C0hbYkSc/jBmggIrXJWlZM6pSETsEPGqZOndr2uuuR5rF169a2HoHPdurUKZM4CO1WTPqaDaAd+GFGKdIQkxAn9RuEWcTRyN2KSUgiSgF5aWzPTeA/lN5rZubMmR2bE4SIC4nJoltgAV/dVefZm72AtctUCJU2CMJ327hxY9t7EHbkyJFseq+EJSY16RPo3Dkq1kkr7+q0bNmyDuLQcZBEPYmHVdOBiJyIlrRDq41YPWfXOxUysi5fvtyaj+2BpcnsUV/oSoEMOk2CQGlr4ckhBwaetBhjCwH0ZHtJROPJkyc7UjcYLDjmrH7ADTEBXFfOYmB0k9oYBOjJ8b4aOYSe7QkKcYhFlq3QYLQhSidNmtS2RATwy8YOM3EQJsUjKiaWZ+vZToUQgzhkHXudb/PW5YMHD9yZM2faPsMwoc7RciYJXbGuBqJ1UIGKKLv915jsvgtJxCZDubdXr165mzdvtr1Hz5LONA8jrUwKPqsmVesKa49S3Q4WxmRPUEYdTjgiUcfUwLx589ySJUva3oMkP6IYddq6HMS4o55xBJBUeRjzfa4Zdeg56QZ43LhxoyPo7Lf1kNt7oO8wWAbNwaYjIv5lhyS7kRf96dvm5Jah8vfvX3flyhX35cuX6HfzFHOToS1H4BenCaHvO8pr8iDuwoUL7tevX+b5ZdbBair0xkFIlFDlW4ZknEClsp/TzXyAKVOmmHWFVSbDNw1l1+4f90U6IY/q4V27dpnE9bJ+v87QEydjqx/UamVVPRG+mwkNTYN+9tjkwzEx+atCm/X9WvWtDtAb68Wy9LXa1UmvCDDIpPkyOQ5ZwSzJ4jMrvFcr0rSjOUh+GcT4LSg5ugkW1Io0/SCDQBojh0hPlaJdah+tkVYrnTZowP8iq1F1TgMBBauufyB33x1v+NWFYmT5KmppgHC+NkAgbmRkpD3yn9QIseXymoTQFGQmIOKTxiZIWpvAatenVqRVXf2nTrAWMsPnKrMZHz6bJq5jvce6QK8J1cQNgKxlJapMPdZSR64/UivS9NztpkVEdKcrs5alhhWP9NeqlfWopzhZScI6QxseegZRGeg5a8C3Re1Mfl1ScP36ddcUaMuv24iOJtz7sbUjTS4qBvKmstYJoUauiuD3k5qhyr7QdUHMeCgLa1Ear9NquemdXgmum4fvJ6w1lqsuDhNrg1qSpleJK7K3TF0Q2jSd94uSZ60kK1e3qyVpQK6PVWXp2/FC3mp6jBhKKOiY2h3gtUV64TWM6wDETRPLDfSakXmH3w8g9Jlug8ZtTt4kVF0kLUYYmCCtD/DrQ5YhMGbA9L3ucdjh0y8kOHW5gU/VEEmJTcL4Pz/f7mgoAbYkAAAAAElFTkSuQmCC"]
}
]
}响应
json
{
"model": "llava",
"created_at": "2023-12-13T22:42:50. 203334Z",
"message": {
"role": "assistant",
"content": " The image features a cute, little pig with an angry facial expression. It's wearing a heart on its shirt and is waving in the air. This scene appears to be part of a drawing or sketching project. ",
"images": null
},
"done": true,
"total_duration": 1668506709,
"load_duration": 1986209,
"prompt_eval_count": 26,
"prompt_eval_duration": 359682000,
"eval_count": 83,
"eval_duration": 1303285000
}聊天请求（可复现输出）
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "Hello! "
}
],
"options": {
"seed": 101,
"temperature": 0
}
}'响应
json
{
"model": "llama3. 2",
"created_at": "2023-12-12T14:13:43. 416799Z",
"message": {
"role": "assistant",
"content": "Hello! How are you today? "
},
"done": true,
"total_duration": 5191566416,
"load_duration": 2154458,
"prompt_eval_count": 26,
"prompt_eval_duration": 383809000,
"eval_count": 298,
"eval_duration": 4799921000
}聊天请求（带工具）
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [
{
"role": "user",
"content": "What is the weather today in Paris? "
}
],
"stream": false,
"tools": [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The location to get the weather for, e. g. San Francisco, CA"
},
"format": {
"type": "string",
"description": "The format to return the weather in, e. g. 'celsius' or 'fahrenheit'",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location", "format"]
}
}
}
]
}'响应
json
{
"model": "llama3. 2",
"created_at": "2024-07-22T20:33:28. 123648Z",
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_current_weather",
"arguments": {
"format": "celsius",
"location": "Paris, FR"
}
}
}
]
},
"done_reason": "stop",
"done": true,
"total_duration": 885095291,
"load_duration": 3753500,
"prompt_eval_count": 122,
"prompt_eval_duration": 328493000,
"eval_count": 33,
"eval_duration": 552222000
}加载模型
如果 messages 数组为空，模型将被加载到内存中。
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": []
}'响应
json
{
"model": "llama3. 2",
"created_at": "2024-09-12T21:17:29. 110811Z",
"message": {
"role": "assistant",
"content": ""
},
"done_reason": "load",
"done": true
}卸载模型
如果 messages 数组为空且 keep_alive 参数设置为 0，模型将从内存中卸载。
请求
shell
curl http://localhost:11434/api/chat -d '{
"model": "llama3. 2",
"messages": [],
"keep_alive": 0
}'响应
将返回单个 JSON 对象：
json
{
"model": "llama3. 2",
"created_at": "2024-09-12T21:33:17. 547535Z",
"message": {
"role": "assistant",
"content": ""
},
"done_reason": "unload",
"done": true
}创建模型
POST /api/create可从以下来源创建模型：
- 另一个模型；
- safetensors 目录；或
- GGUF 文件。
如果要从 safetensors 目录或 GGUF 文件创建模型，需要先为每个文件创建 blob，然后在 files 字段中使用与每个 blob 关联的文件名和 SHA256 摘要。
参数
model：要创建的模型的名称from：（可选）用于创建新模型的现有模型的名称files：（可选）文件名到对应 blob 的 SHA256 摘要的字典，用于指定创建模型所用的文件adapters：（可选）文件名到对应 LORA 适配器 blob 的 SHA256 摘要的字典template：（可选）模型的提示词模板renderer：（可选）模型的渲染器名称parser：（可选）模型的解析器名称license：（可选）包含模型许可证的字符串或字符串列表system：（可选）包含模型系统提示词的字符串parameters：（可选）模型的参数字典（参数列表见 Modelfile）messages：（可选）用于创建对话的消息对象列表stream：（可选）如果设为false，响应将作为单个响应对象返回，而非对象流quantize（可选）：对非量化（例如 float16）模型进行量化
量化类型
| Type | 推荐 |
|---|---|
| q4_K_M | * |
| q4_K_S | |
| q8_0 | * |
示例
创建新模型
从现有模型创建新模型。
请求
shell
curl http://localhost:11434/api/create -d '{
"model": "mario",
"from": "llama3.2",
"system": "You are Mario from Super Mario Bros."
}'响应
将返回 JSON 对象流：
json
{"status":"reading model metadata"}
{"status":"creating system layer"}
{"status":"using already created layer sha256:22f7f8ef5f4c791c1b03d7eb414399294764d7cc82c7e94aa81a1feb80a983a2"}
{"status":"using already created layer sha256:8c17c2ebb0ea011be9981cc3922db8ca8fa61e828c5d3f44cb6ae342bf80460b"}
{"status":"using already created layer sha256:7c23fb36d80141c4ab8cdbb61ee4790102ebd2bf7aeff414453177d4f2110e5d"}
{"status":"using already created layer sha256:2e0493f67d0c8c9c68a8aeacdf6a38a2151cb3c4c1d42accf296e19810527988"}
{"status":"using already created layer sha256:2759286baa875dc22de5394b4a925701b1896a7e3f8e53275c36f75a877a82c9"}
{"status":"writing layer sha256:df30045fe90f0d750db82a058109cecd6d4de9c90a3d75b19c09e5f64580bb42"}
{"status":"writing layer sha256:f18a68eb09bf925bb1b669490407c1b1251c5db98dc4d3d81f3088498ea55690"}
{"status":"writing manifest"}
{"status":"success"}量化模型
对非量化模型进行量化。
请求
shell
curl http://localhost:11434/api/create -d '{
"model": "llama3.2:quantized",
"from": "llama3.2:3b-instruct-fp16",
"quantize": "q4_K_M"
}'响应
将返回 JSON 对象流：
json
{"status":"quantizing F16 model to Q4_K_M","digest":"0","total":6433687776,"completed":12302}
{"status":"quantizing F16 model to Q4_K_M","digest":"0","total":6433687776,"completed":6433687552}
{"status":"verifying conversion"}
{"status":"creating new layer sha256:fb7f4f211b89c6c4928ff4ddb73db9f9c0cfca3e000c3e40d6cf27ddc6ca72eb"}
{"status":"using existing layer sha256:966de95ca8a62200913e3f8bfbf84c8494536f1b94b49166851e76644e966396"}
{"status":"using existing layer sha256:fcc5a6bec9daf9b561a68827b67ab6088e1dba9d1fa2a50d7bbcc8384e0a265d"}
{"status":"using existing layer sha256:a70ff7e570d97baaf4e62ac6e6ad9975e04caa6d900d3742d37698494479e0cd"}
{"status":"using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb"}
{"status":"writing manifest"}
{"status":"success"}从 GGUF 创建模型
从 GGUF 文件创建模型。files 参数需要填入要使用的 GGUF 文件的文件名和 SHA256 摘要。调用此 API 前，请使用 /api/blobs/:digest 将 GGUF 文件推送到服务器。
请求
shell
curl http://localhost:11434/api/create -d '{
"model": "my-gguf-model",
"files": {
"test.gguf": "sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"
}
}'响应
将返回 JSON 对象流：
json
{"status":"parsing GGUF"}
{"status":"using existing layer sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"}
{"status":"writing manifest"}
{"status":"success"}从 Safetensors 目录创建模型
files 参数需要包含 safetensors 模型的文件字典，其中包含每个文件的文件名和 SHA256 摘要。调用此 API 前，请先使用 /api/blobs/:digest 将每个文件推送到服务器。文件会保留在缓存中，直到 Ollama 服务器重启。
请求
shell
curl http://localhost:11434/api/create -d '{
"model": "fred",
"files": {
"config.json": "sha256:dd3443e529fb2290423a0c65c2d633e67b419d273f170259e27297219828e389",
"generation_config.json": "sha256:88effbb63300dbbc7390143fbbdd9d9fa50587b37e8bfd16c8c90d4970a74a36",
"special_tokens_map.json": "sha256:b7455f0e8f00539108837bfa586c4fbf424e31f8717819a6798be74bef813d05",
"tokenizer.json": "sha256:bbc1904d35169c542dffbe1f7589a5994ec7426d9e5b609d07bab876f32e97ab",
"tokenizer_config.json": "sha256:24e8a6dc2547164b7002e3125f10b415105644fcf02bf9ad8b674c87b1eaaed6",
"model.safetensors": "sha256:1ff795ff6a07e6a68085d206fb84417da2f083f68391c2843cd2b8ac6df8538f"
}
}'响应
将返回 JSON 对象流：
shell
{"status":"converting model"}
{"status":"creating new layer sha256:05ca5b813af4a53d2c2922933936e398958855c44ee534858fcfd830940618b6"}
{"status":"using autodetected template llama3-instruct"}
{"status":"using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb"}
{"status":"writing manifest"}
{"status":"success"}检查 Blob 是否存在
shell
HEAD /api/blobs/:digest确保创建模型时使用的文件 Blob（二进制大对象）存在于服务器上。此操作检查的是你本地的 Ollama 服务器，而非 ollama.com。
查询参数
digest：blob 的 SHA256 摘要
示例
请求
shell
curl -I http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2响应
如果 blob 存在则返回 200 OK，不存在则返回 404 Not Found。
推送 Blob
POST /api/blobs/:digest将文件推送到 Ollama 服务器以创建“Blob”（二进制大对象）。
查询参数
digest：文件的预期 SHA256 摘要
示例
请求
shell
curl -T model.gguf -X POST http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2响应
如果 blob 成功创建则返回 201 Created，如果使用的摘要不符合预期则返回 400 Bad Request。
列出本地模型
GET /api/tags列出本地可用的模型。
示例
请求
shell
curl http://localhost:11434/api/tags响应
将返回单个 JSON 对象。
json
{
"models": [
{
"name": "deepseek-r1:latest",
"model": "deepseek-r1:latest",
"modified_at": "2025-05-10T08:06:48.639712648-07:00",
"size": 4683075271,
"digest": "0a8c266910232fd3291e71e5ba1e058cc5af9d411192cf88b6d30e92b6e73163",
"details": {
"parent_model": "",
"format": "gguf",
"family": "qwen2",
"families": ["qwen2"],
"parameter_size": "7.6B",
"quantization_level": "Q4_K_M"
}
},
{
"name": "llama3.2:latest",
"model": "llama3.2:latest",
"modified_at": "2025-05-04T17:37:44.706015396-07:00",
"size": 2019393189,
"digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": ["llama"],
"parameter_size": "3.2B",
"quantization_level": "Q4_K_M"
}
}
]
}查看模型信息
POST /api/show显示模型的详细信息，包括模型文件（Modelfile）、模板、参数、许可证、系统提示词等。
参数
model：要查看的模型名称verbose：（可选）如果设置为true，则返回详细响应字段的完整数据
示例
请求
shell
curl http://localhost:11434/api/show -d '{
"model": "llava"
}'响应
json5
{
modelfile: '# Modelfile generated by "ollama show"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llava:latest\n\nFROM /Users/matt/.ollama/models/blobs/sha256:200765e1283640ffbd013184bf496e261032fa75b99498a9613be4e94d63ad52\nTEMPLATE """{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: """\nPARAMETER num_ctx 4096\nPARAMETER stop "\u003c/s\u003e"\nPARAMETER stop "USER:"\nPARAMETER stop "ASSISTANT:"',
parameters: 'num_keep 24\nstop "<|start_header_id|>"\nstop "<|end_header_id|>"\nstop "<|eot_id|>"',
template: "{{ if .System }}<|start_header_id|>system<|end_header_id|>\n\n{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>\n\n{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>\n\n{{ .Response }}<|eot_id|>",
details: {
parent_model: "",
format: "gguf",
family: "llama",
families: ["llama"],
parameter_size: "8.0B",
quantization_level: "Q4_0",
},
model_info: {
"general.architecture": "llama",
"general.file_type": 2,
"general.parameter_count": 8030261248,
"general.quantization_version": 2,
"llama.attention.head_count": 32,
"llama.attention.head_count_kv": 8,
"llama.attention.layer_norm_rms_epsilon": 0.00001,
"llama.block_count": 32,
"llama.context_length": 8192,
"llama.embedding_length": 4096,
"llama.feed_forward_length": 14336,
"llama.rope.dimension_count": 128,
"llama.rope.freq_base": 500000,
"llama.vocab_size": 128256,
"tokenizer.ggml.bos_token_id": 128000,
"tokenizer.ggml.eos_token_id": 128009,
"tokenizer.ggml.merges": [], // populates if `verbose=true`
"tokenizer.ggml.model": "gpt2",
"tokenizer.ggml.pre": "llama-bpe",
"tokenizer.ggml.token_type": [], // populates if `verbose=true`
"tokenizer.ggml.tokens": [], // populates if `verbose=true`
},
capabilities: ["completion", "vision"],
}复制模型
POST /api/copy复制模型。基于现有模型创建一个名称不同的新模型。
示例
请求
shell
curl http://localhost:11434/api/copy -d '{
"source": "llama3.2",
"destination": "llama3-backup"
}'响应
操作成功则返回 200 OK，如果源模型不存在则返回 404 Not Found。
删除模型
DELETE /api/delete删除模型及其相关数据。
参数
model：要删除的模型名称
示例
请求
shell
curl -X DELETE http://localhost:11434/api/delete -d '{
"model": "llama3:13b"
}'响应
操作成功则返回 200 OK，如果要删除的模型不存在则返回 404 Not Found。
拉取模型
POST /api/pull从 Ollama 库下载模型。已取消的拉取任务会从中断的位置继续下载，多次调用会共享相同的下载进度。
参数
model：要拉取的模型名称insecure：（可选）允许与库建立非安全连接。仅在开发过程中从你自己的库拉取模型时使用此参数。stream：（可选）如果设置为false，响应将作为单个响应对象返回，而非对象流。
示例
请求
shell
curl http://localhost:11434/api/pull -d '{
"model": "llama3.2"
}'响应
如果未指定 stream 或将其设置为 true，则返回 JSON 对象流：
第一个对象是清单：
json
{
"status": "pulling manifest"
}随后会返回一系列下载响应。在下载完成之前，可能不会包含 completed 键。需要下载的文件数量取决于清单中指定的层数。
json
{
"status": "pulling digestname",
"digest": "digestname",
"total": 2142590208,
"completed": 241970
}所有文件下载完成后，最终响应如下：
json
{
"status": "verifying sha256 digest"
}
{
"status": "writing manifest"
}
{
"status": "removing any unused layers"
}
{
"status": "success"
}如果 stream 设置为 false，则响应为单个 JSON 对象：
json
{
"status": "success"
}推送模型
POST /api/push将模型上传到模型库。需要先在 ollama.ai 注册并添加公钥。
参数
model：要推送的模型名称，格式为<namespace>/<model>:<tag>insecure：（可选）允许与库建立非安全连接。仅在开发过程中推送到你自己的库时使用此参数。stream：（可选）如果设置为false，响应将作为单个响应对象返回，而非对象流。
示例
请求
shell
curl http://localhost:11434/api/push -d '{
"model": "mattw/pygmalion:latest"
}'响应
如果未指定 stream 或将其设置为 true，则返回 JSON 对象流：
json
{ "status": "retrieving manifest" }随后：
json
{
"status": "starting upload",
"digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
"total": 1928429856
}随后会返回一系列上传响应：
json
{
"status": "starting upload",
"digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
"total": 1928429856
}最后，上传完成后：
json
{"status":"pushing manifest"}
{"status":"success"}如果 stream 设置为 false，则响应为单个 JSON 对象：
json
{ "status": "success" }生成嵌入向量
POST /api/embed从模型生成嵌入向量
参数
model：用于生成嵌入向量的模型名称input：用于生成嵌入向量的文本或文本列表
高级参数：
truncate：截断每个输入的末尾以适配上下文长度。如果设置为false且超出上下文长度，则返回错误。默认值为trueoptions：Modelfile 文档中列出的额外模型参数，例如temperaturekeep_alive：控制请求完成后模型在内存中保留的时长（默认值：5m）dimensions：嵌入向量的维度数
示例
请求
shell
curl http://localhost:11434/api/embed -d '{
"model": "all-minilm",
"input": "Why is the sky blue?"
}'响应
json
{
"model": "all-minilm",
"embeddings": [
[
0.010071029, -0.0017594862, 0.05007221, 0.04692972, 0.054916814,
0.008599704, 0.105441414, -0.025878139, 0.12958129, 0.031952348
]
],
"total_duration": 14143917,
"load_duration": 1019500,
"prompt_eval_count": 8
}请求（多输入）
shell
curl http://localhost:11434/api/embed -d '{
"model": "all-minilm",
"input": ["Why is the sky blue?", "Why is the grass green?"]
}'响应
json
{
"model": "all-minilm",
"embeddings": [
[
0.010071029, -0.0017594862, 0.05007221, 0.04692972, 0.054916814,
0.008599704, 0.105441414, -0.025878139, 0.12958129, 0.031952348
],
[
-0.0098027075, 0.06042469, 0.025257962, -0.006364387, 0.07272725,
0.017194884, 0.09032035, -0.051705178, 0.09951512, 0.09072481
]
]
}列出运行中的模型
GET /api/ps列出当前已加载到内存中的模型。
示例
请求
shell
curl http://localhost:11434/api/ps响应
将返回单个 JSON 对象。
json
{
"models": [
{
"name": "mistral:latest",
"model": "mistral:latest",
"size": 5137025024,
"digest": "2ae6f6dd7a3dd734790bbbf58b8909a606e0e7e97e94b7604e0aa7ae4490e6d8",
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": ["llama"],
"parameter_size": "7.2B",
"quantization_level": "Q4_0"
},
"expires_at": "2024-06-04T14:38:31.83753-07:00",
"size_vram": 5137025024
}
]
}生成嵌入向量
注意：此端点已被
/api/embed取代
POST /api/embeddings从模型生成嵌入向量
参数
model：用于生成嵌入向量的模型名称prompt：用于生成嵌入向量的文本
高级参数：
options：Modelfile 文档中列出的额外模型参数，例如temperaturekeep_alive：控制请求完成后模型在内存中保留的时长（默认值：5m）
示例
请求
shell
curl http://localhost:11434/api/embeddings -d '{
"model": "all-minilm",
"prompt": "Here is an article about llamas..."
}'响应
json
{
"embedding": [
0.5670403838157654, 0.009260174818336964, 0.23178744316101074,
-0.2916173040866852, -0.8924556970596313, 0.8785552978515625,
-0.34576427936553955, 0.5742510557174683, -0.04222835972905159,
-0.137906014919281
]
}版本
GET /api/version获取 Ollama 版本
示例
请求
shell
curl http://localhost:11434/api/version响应
json
{
"version": "0.5.1"
}实验性功能
图像生成（实验性）
WARNING
图像生成功能仍处于实验阶段，未来版本可能会发生变更。
使用图像生成模型时，现在可以通过标准的 /api/generate 端点实现图像生成。API 会自动检测是否正在使用图像生成模型。
完整的 API 文档请参阅生成补全内容部分，实验性图像生成参数（width、height、steps）的说明也在该部分。
示例
请求
shell
curl http://localhost:11434/api/generate -d '{
"model": "x/z-image-turbo",
"prompt": "a sunset over mountains",
"width": 1024,
"height": 768
}'响应（流式）
生成过程中的进度更新：
json
{
"model": "x/z-image-turbo",
"created_at": "2024-01-15T10:30:00.000000Z",
"completed": 5,
"total": 20,
"done": false
}最终响应
json
{
"model": "x/z-image-turbo",
"created_at": "2024-01-15T10:30:15.000000Z",
"image": "iVBORw0KGgoAAAANSUhEUg...",
"done": true,
"done_reason": "stop",
"total_duration": 15000000000,
"load_duration": 2000000000
}