> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fastino.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use https://docs.fastino.ai/llms.txt to discover and navigate pages. Use https://docs.fastino.ai/llms-full.txt when you need the complete documentation corpus. Use https://docs.fastino.ai/openapi.json as the source of truth for customer-facing routes. For GLiDE decision inference, call POST https://api.fastino.ai/v1/systemone with model fastino/GLiDE. Create managed config jobs with POST /v1/training/jobs using base_model. For custom training loops, native JSON clients use the public operations under /v1/training/jobs and /v1/training/usage. Existing Tinker clients use tinker==0.32.0 with TINKER_BASE_URL=https://api.fastino.ai/v1/training/compat/tinker and TINKER_CREDENTIAL_CMD. Compatibility child routes are private and absent from OpenAPI. Auto Train is private access and has no public route; direct interested users to sales@fastino.ai. Do not infer undocumented routes. Read API keys from FASTINO_API_KEY and never embed credentials in code, logs, or reports.

# 部署交互式任务检查点

> 将交互式任务的 sampler 检查点部署为训练好的模型，再通过 POST /v1/chat/completions 调用。

`POST /v1/training/jobs/{job_id}/checkpoints/sampler_weights/{name}/deploy`

将任务的某个 sampler 检查点作为训练好的模型提供服务。使用 [`POST /v1/chat/completions`](/cn/api-reference/inference/chat-completions) 并传入 `"model": "<model_id>"` 调用它。部署适用于受支持的基础模型；其他基础模型返回 `400`。

在服务引擎加载模型之前，其 `status` 为 `deploying`，之后为 `deployed`。再次部署同一检查点会返回同一个模型及其当前状态，因此可以重复调用来查看进度。如果之前的尝试失败，重复调用会重试。

<ParamField header="X-API-Key" type="string" required>
  您的 Fastino API 密钥。
</ParamField>

<ParamField path="job_id" type="string" required>
  交互式任务 ID。
</ParamField>

<ParamField path="name" type="string" required>
  使用 [`save-weights-for-sampler`](/cn/api-reference/training-jobs/interactive/save-weights-for-sampler) 保存的 sampler 检查点名称。
</ParamField>

<ParamField body="model_name" type="string">
  最多 64 个字母、数字、连字符和下划线，须以字母或数字开头和结尾。省略时根据检查点名称生成。请求体可省略。
</ParamField>

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/checkpoints/sampler_weights/step-000100/deploy" \
    -H "X-API-Key: $FASTINO_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"model_name": "support-replies-v1"}'
  ```
</RequestExample>

<ResponseField name="model_id" type="string">
  训练好的模型 ID。推理时将其作为 `model` 传入。
</ResponseField>

<ResponseField name="job_id" type="string">
  保存该检查点的交互式任务。
</ResponseField>

<ResponseField name="checkpoint_id" type="string">
  `sampler_weights/<name>`。
</ResponseField>

<ResponseField name="base_model" type="string">
  模型的基础模型。
</ResponseField>

<ResponseField name="project_id" type="string | null">
  任务所属的项目（如有）。
</ResponseField>

<ResponseField name="status" type="string">
  `deploying` 或 `deployed`。
</ResponseField>

<ResponseExample>
  ```json Response theme={null}
  {
    "model_id": "MODEL_ID",
    "job_id": "SESSION_ID:train:0",
    "checkpoint_id": "sampler_weights/step-000100",
    "base_model": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
    "project_id": null,
    "status": "deploying"
  }
  ```
</ResponseExample>

| 状态 | 含义 |
| - | - |
| `400` | 任务的基础模型暂不支持服务，或该检查点不是服务引擎接受的 PEFT 适配器。 |
| `404` | 任务或 sampler 检查点不存在、属于其他团队，或没有文件。 |
| `409` | `model_name` 已被其他模型使用，或由该检查点提供服务的模型已被删除。请以新名称保存权重后再部署。 |
| `422` | `model_name` 无效，或请求体包含未知字段。 |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.