diff --git a/chat_completion.yaml b/chat_completion.yaml
new file mode 100644
index 000000000..f2e69007a
--- /dev/null
+++ b/chat_completion.yaml
@@ -0,0 +1,157 @@
+openapi: 3.0.0
+info:
+  title: Single Inference API (chat_completion)
+  version: 0.0.1
+components:
+  schemas:
+    Tool:
+      type: object
+      description: A tool that can be used by an agent to perform specific tasks.
+      properties:
+        name:
+          type: string
+          description: The name of the tool.
+        description:
+          type: string
+          description: A brief description of what the tool does and how it should be used.
+        parameters:
+          type: array
+          items:
+            $ref: '#/components/schemas/ToolParameter'
+        returnValue:
+          $ref: '#/components/schemas/ToolReturnValue'
+    ToolParameter:
+      type: object
+      properties:
+        type:
+          type: string
+          enum: [string, int, float, list, bool]
+          description: The data type of the parameter.
+        itemType:
+          type: string
+          description: The type of items in the parameter if it is a list.
+        description:
+          type: string
+          description: Details about what the parameter is used for and any constraints.
+    ToolReturnValue:
+      type: object
+      properties:
+        type:
+          type: string
+          enum: [string, int, float, list, bool]
+          description: The data type of the return value.
+        itemType:
+          type: string
+          description: The type of items in the return value if it is a list.
+        description:
+          type: string
+          description: Details about the significance of the return value.
+    Attachment:
+      type: object
+      properties:
+        uri:
+          type: string
+          description: URI of the attachment.
+        mime-type:
+          type: string
+          description: MIME type of the attachment.
+    Message:
+      type: object
+      properties:
+        role:
+          type: string
+          description: Role of the entity in the message.
+        text:
+          type: string
+          description: Text content of the message.
+        attachments:
+          type: array
+          items:
+            $ref: '#/components/schemas/Attachment'
+    Completion:
+      type: object
+      properties:
+        id:
+          type: string
+          description: Unique identifier for the completion.
+        role:
+          type: string
+          description: Role of the entity generating the completion.
+        text:
+          type: string
+          description: Text content of the completion.
+        attachments:
+          type: array
+          items:
+            $ref: '#/components/schemas/Attachment'
+        tokens:
+          type: array
+          items:
+            type: integer
+        logprobs:
+          type: array
+          items:
+            type: number
+        finish_reason:
+          type: string
+          description: Reason for completion termination.
+        # TODO: Add `tool_choice` --
+        # for eg. "auto": use model's guess, how to force to use particular tool, how to disbale inbuilt tools
+paths:
+  /chat_completion/:
+    post:
+      summary: Submit a chat completion request
+      description: Submit a chat completion request
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                messages:
+                  type: array
+                  items:
+                    $ref: '#/components/schemas/Message'
+                model:
+                  type: string
+                  description: Model identifier
+                logprobs:
+                  type: boolean
+                  description: Whether to include log probabilities in the output
+                max_tokens:
+                  type: integer
+                  description: Maximum number of tokens to generate
+                n_completions:
+                  type: integer
+                  description: Number of completions to generate
+                temperature:
+                  type: number
+                  format: float
+                  description: Temperature setting for the generation
+                top_p:
+                  type: number
+                  format: float
+                  description: Top p setting for the generation
+                tools:
+                  type: array
+                  items:
+                    $ref: '#/components/schemas/Tool'
+      responses:
+        '200':
+          description: Chat completion request processed successfully
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  id:
+                    type: string
+                    description: Unique identifier for the completion request
+                  completions:
+                    type: array
+                    items:
+                      $ref: '#/components/schemas/Completion'
+                  model:
+                    type: string
+                    description: Model used for generating completions